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

    Neuronpedia

    INDEX
    Explanations

    passive actions or states described using specific verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating obligations, tendencies, and future actions related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    polit
    -0.74
    politics
    -0.69
     entails
    -0.64
     transpired
    -0.63
     heals
    -0.58
    ),"
    -0.57
    cler
    -0.56
    aman
    -0.55
    /+
    -0.54
     geop
    -0.53
    POSITIVE LOGITS
    ŃĶ
    0.80
     nevertheless
    0.74
     attest
    0.73
    Ĥİ
    0.69
     nonetheless
    0.69
     likewise
    0.67
     themselves
    0.65
    ledged
    0.61
    hap
    0.60
    ushima
    0.60
    Act Density 0.532%

    No Known Activations