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

    Neuronpedia

    INDEX
    Explanations

    female first names

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns, particularly related to people and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickr
    -0.78
    anyl
    -0.76
    bably
    -0.71
     deterrent
    -0.68
     sleeper
    -0.68
    uggest
    -0.68
     commercially
    -0.67
     dictators
    -0.66
     preempt
    -0.64
    undown
    -0.63
    POSITIVE LOGITS
    hyde
    1.03
    abeth
    0.90
    cia
    0.89
     Rae
    0.82
    ette
    0.82
    Anne
    0.80
     Marie
    0.78
    otte
    0.78
     Chal
    0.77
     Cohn
    0.77
    Act Density 0.307%

    No Known Activations