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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating willingness or ability to take action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izable
    -0.76
     Acquisition
    -0.67
     attempt
    -0.65
     Manufact
    -0.63
     fade
    -0.63
     fray
    -0.60
     Must
    -0.59
     reperto
    -0.58
     Wid
    -0.57
     circulation
    -0.57
    POSITIVE LOGITS
     bothered
    1.14
     persuaded
    0.99
     sure
    0.96
     swayed
    0.96
     trusted
    0.95
     forgiven
    0.94
     confident
    0.91
     fooled
    0.90
     tempted
    0.88
     assured
    0.86
    Act Density 0.076%

    No Known Activations