Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    events or incidents that happen after some specific time or action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    temporal references or words related to timing and sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.02
    2:0.11
    3:0.11
    4:0.34
    5:0.05
    6:0.05
    7:0.02
    8:0.05
    9:0.07
    10:0.05
    11:0.02
    Negative Logits
    minecraft
    -1.98
    smart
    -1.56
    crypt
    -1.43
    vg
    -1.42
     Liter
    -1.40
    photos
    -1.36
    Cos
    -1.35
    initely
    -1.33
    bryce
    -1.32
    uv
    -1.31
    POSITIVE LOGITS
    ITNESS
    1.57
     firing
    1.40
    iatus
    1.33
    ██
    1.33
     graduation
    1.31
     fulfillment
    1.26
     rejo
    1.26
     succeeded
    1.22
     repr
    1.21
     retribution
    1.21
    Act Density 0.007%

    No Known Activations