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

    Neuronpedia

    INDEX
    Explanations

    action-related verbs or phrases associated with discussing or expressing opinions

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sloan
    -0.73
    pmwiki
    -0.72
     Fas
    -0.66
     Bastard
    -0.59
     Bronze
    -0.59
     Anon
    -0.58
     sqor
    -0.58
     propensity
    -0.58
     ham
    -0.57
     Shack
    -0.57
    POSITIVE LOGITS
    uate
    0.80
    enance
    0.79
    tails
    0.76
    ezvous
    0.72
     besides
    0.71
    abouts
    0.70
    tail
    0.68
    iate
    0.68
    agine
    0.67
    idious
    0.66
    Act Density 0.228%

    No Known Activations