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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restrictions or rules

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrace
    -0.83
     challeng
    -0.81
     horizont
    -0.75
     describ
    -0.69
     coerc
    -0.68
     advoc
    -0.67
     segreg
    -0.66
    arded
    -0.66
     decap
    -0.65
     elim
    -0.65
    POSITIVE LOGITS
    Enlarge
    0.79
     âĢķ
    0.75
     Thieves
    0.73
    >>\
    0.71
    toggle
    0.70
    Whe
    0.68
     Asked
    0.68
    BuyableInstoreAndOnline
    0.68
     Hearing
    0.66
     ["
    0.65
    Act Density 0.063%

    No Known Activations