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

    Neuronpedia

    INDEX
    Explanations

    verbs related to belief, assumption, and concession

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief, assumptions, and statements made by individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agnetic
    -0.76
    gie
    -0.69
    gro
    -0.69
    berus
    -0.68
    tesy
    -0.67
    ibur
    -0.65
    mone
    -0.65
    phe
    -0.65
    gren
    -0.64
    elight
    -0.63
    POSITIVE LOGITS
     furthermore
    0.86
     passionately
    0.80
     that
    0.80
     notions
    0.78
     moreover
    0.77
     how
    0.76
     differently
    0.74
     implicitly
    0.74
     propositions
    0.73
     imagining
    0.72
    Act Density 0.399%

    No Known Activations