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

    Neuronpedia

    INDEX
    Explanations

    actions or activities being performed by someone

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to do" and related action verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nown
    -0.82
    endant
    -0.67
    ersen
    -0.66
    izons
    -0.65
    ère
    -0.64
     Saud
    -0.64
    oglu
    -0.61
    nen
    -0.60
    ikan
    -0.60
    hid
    -0.60
    POSITIVE LOGITS
     regard
    0.69
     mode
    0.68
     circles
    0.67
     materials
    0.66
     crowds
    0.66
     hearts
    0.65
     venues
    0.65
     roles
    0.64
     mosqu
    0.64
     spheres
    0.62
    Act Density 0.127%

    No Known Activations