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

    Neuronpedia

    INDEX
    Explanations

    assertive statements about knowledge or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.09
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    edged
    -1.67
     illustrating
    -1.66
     blot
    -1.64
     gesture
    -1.61
     Frie
    -1.56
     cautioned
    -1.55
     Frem
    -1.53
     futile
    -1.50
     sketch
    -1.44
     Hasan
    -1.44
    POSITIVE LOGITS
    obyl
    1.99
    osphere
    1.82
     Alone
    1.75
    emies
    1.74
    Sov
    1.72
    hesda
    1.66
    HQ
    1.65
    Destroy
    1.58
    ILA
    1.56
     Compared
    1.52
    Act Density 0.000%

    No Known Activations