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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions, decisions, and intentions

    oai_token-act-pair · gpt-3.5-turbo

    verbs that express intention or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fail
    -0.71
    folk
    -0.70
    aminer
    -0.68
    eers
    -0.64
    Eva
    -0.63
    !),
    -0.62
     foothold
    -0.62
    )!
    -0.62
    !).
    -0.61
     conveniently
    -0.61
    POSITIVE LOGITS
     "#
    0.91
     personally
    0.86
     "'
    0.83
     "
    0.75
     "[
    0.75
    poke
    0.75
     Paddock
    0.73
     resign
    0.72
     himself
    0.71
     constituents
    0.69
    Act Density 0.618%

    No Known Activations