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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inevitability or outcomes based on choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.75
    AndEndTag
    -0.73
     ModelExpression
    -0.72
     raiſ
    -0.72
     myſelf
    -0.69
     Efq
    -0.67
     ſind
    -0.67
    @[+][
    -0.67
    requency
    -0.67
     protoimpl
    -0.64
    POSITIVE LOGITS
     doomed
    0.72
     gone
    0.71
     DONE
    0.62
     done
    0.61
     dead
    0.61
     game
    0.60
     GONE
    0.60
    完了
    0.60
     toast
    0.57
     Done
    0.57
    Act Density 0.228%

    No Known Activations