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

    Neuronpedia

    INDEX
    Explanations

    verbs related to ability or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inability or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollah
    -0.63
    rongh
    -0.62
    ghan
    -0.60
     mull
    -0.60
     pepp
    -0.59
    BTC
    -0.57
    ortment
    -0.57
     dotted
    -0.56
    hoe
    -0.55
     quint
    -0.55
    POSITIVE LOGITS
     anymore
    1.17
    uate
    0.91
    urate
    0.83
    athom
    0.80
     anything
    0.78
     nor
    0.77
    ades
    0.71
    gravity
    0.71
     any
    0.70
     anybody
    0.70
    Act Density 0.232%

    No Known Activations