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

    Neuronpedia

    INDEX
    Explanations

    comparisons related to past and present situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.12
    3:0.06
    4:0.09
    5:0.04
    6:0.07
    7:0.12
    8:0.15
    9:0.04
    10:0.10
    11:0.11
    Negative Logits
     narrative
    -1.45
     attribution
    -1.44
     ammunition
    -1.43
     unsub
    -1.43
     dx
    -1.43
     moniker
    -1.43
     poster
    -1.42
     fragment
    -1.42
     counter
    -1.41
     piercing
    -1.41
    POSITIVE LOGITS
    flation
    1.73
     Unemployment
    1.58
    oyer
    1.57
    opolis
    1.56
    ynes
    1.51
     Hollande
    1.50
    "},"
    1.50
    ropolitan
    1.48
    staff
    1.48
    ruary
    1.47
    Act Density 0.001%

    No Known Activations