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

    Neuronpedia

    INDEX
    Explanations

    references to significant historical events or legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.09
    2:0.08
    3:0.07
    4:0.09
    5:0.07
    6:0.10
    7:0.09
    8:0.06
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    schild
    -1.88
     Collider
    -1.61
    ourke
    -1.61
    pn
    -1.45
     Koch
    -1.44
    chemist
    -1.44
     awa
    -1.42
    ambers
    -1.42
    everal
    -1.41
    outher
    -1.41
    POSITIVE LOGITS
    arsity
    1.51
    VALUE
    1.50
    iture
    1.47
    ftime
    1.46
    uploads
    1.44
    サ
    1.43
    ヘラ
    1.43
    eworld
    1.42
    Frames
    1.42
    ument
    1.42
    Act Density 0.000%

    No Known Activations