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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating concern or caution regarding events or actions affecting a person's legacy or brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.38
     myſelf
    -1.29
     purpoſe
    -1.22
     iſt
    -1.21
     houſe
    -1.20
    NUMX
    -1.20
     uſe
    -1.19
     Jefus
    -1.18
     faſt
    -1.17
     pleaſure
    -1.17
    POSITIVE LOGITS
     (
    0.95
    (
    0.83
     /
    0.77
    ,
    0.76
    /
    0.74
    -
    0.71
    :
    0.70
     [
    0.68
    ;
    0.68
     -
    0.68
    Act Density 2.086%

    No Known Activations