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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal permission or action

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating ability or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geist
    -0.63
     APPLIC
    -0.63
    Blade
    -0.61
     âĺħ
    -0.61
     paradigm
    -0.60
     Casino
    -0.60
     competitor
    -0.59
    soType
    -0.59
     Sandwich
    -0.58
     Mant
    -0.57
    POSITIVE LOGITS
    't
    1.34
    adian
    1.17
    isters
    1.09
    berra
    1.06
     attest
    0.98
     be
    0.89
     afford
    0.89
     easily
    0.84
     determine
    0.83
     decide
    0.82
    Act Density 0.169%

    No Known Activations