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

    Neuronpedia

    INDEX
    Explanations

    instances of apostrophes indicating possession or contraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    numerusform
    -0.56
     H
    -0.53
    <bos>
    -0.51
    ,
    -0.50
     منهم
    -0.49
    RTS
    -0.49
     
    -0.49
     “
    -0.48
     J
    -0.48
     contar
    -0.48
    POSITIVE LOGITS
     myſelf
    1.18
     itſelf
    0.99
     Majefty
    0.99
     doubtnut
    0.95
     ―――――
    0.95
     ſche
    0.93
     Efq
    0.92
     purpoſe
    0.91
     auffi
    0.91
     pleaſure
    0.90
    Act Density 0.293%

    No Known Activations