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

    Neuronpedia

    INDEX
    Explanations

    exclamatory expressions or responses indicating surprise or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelves
    -0.72
     myſelf
    -0.71
    ſelf
    -0.67
     useRouter
    -0.64
     Houſe
    -0.63
     Majefty
    -0.61
    WireFormatLite
    -0.61
    StateToProps
    -0.61
    SharedDtor
    -0.60
    []
    -0.58
    POSITIVE LOGITS
     yes
    0.90
     yeah
    0.89
     oh
    0.80
    yeah
    0.76
     Oh
    0.74
    Oh
    0.71
    yes
    0.68
    hh
    0.68
     forgot
    0.67
    CloseOperation
    0.67
    Act Density 0.029%

    No Known Activations