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

    Neuronpedia

    INDEX
    Explanations

    single verbs in the infinitive form

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating intention or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lif
    -0.69
     yourselves
    -0.67
     juven
    -0.67
    taboola
    -0.64
    eele
    -0.63
     harms
    -0.63
     Presidency
    -0.62
     belongs
    -0.61
     consequences
    -0.61
     maturity
    -0.60
    POSITIVE LOGITS
     myself
    1.04
     recommend
    0.87
    aido
    0.87
     fond
    0.78
     ende
    0.78
    azon
    0.76
    Ľ
    0.76
     gladly
    0.76
     glad
    0.74
     paraph
    0.73
    Act Density 0.370%

    No Known Activations