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

    Neuronpedia

    INDEX
    Explanations

    verbs in past tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or condition of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĶľ
    -0.74
     Nanto
    -0.72
     elaborated
    -0.70
     concludes
    -0.69
     backdrop
    -0.67
     summarizes
    -0.65
     elabor
    -0.64
     notes
    -0.64
     welf
    -0.63
     Globe
    -0.63
    POSITIVE LOGITS
    nt
    0.74
    cause
    0.71
    overe
    0.70
     somehow
    0.68
     harmless
    0.66
    tan
    0.66
    ovo
    0.65
     "#
    0.65
    piracy
    0.64
     genuine
    0.64
    Act Density 0.651%

    No Known Activations