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

    Neuronpedia

    INDEX
    Explanations

    elements related to document formatting and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.13
    3:0.13
    4:0.08
    5:0.04
    6:0.07
    7:0.07
    8:0.05
    9:0.07
    10:0.16
    11:0.08
    Negative Logits
     regenerate
    -1.59
     Judges
    -1.55
     statues
    -1.46
     Painter
    -1.45
     nominate
    -1.43
     joints
    -1.42
     wise
    -1.38
     Magicka
    -1.38
     wiser
    -1.37
    …)
    -1.37
    POSITIVE LOGITS
    Client
    1.52
    onductor
    1.51
    SSL
    1.51
    ctrl
    1.46
    DERR
    1.43
     VER
    1.43
     encrypted
    1.41
     Alic
    1.40
     MEN
    1.40
    Host
    1.39
    Act Density 0.000%

    No Known Activations