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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to taking decisive measures or steps

    oai_token-act-pair · gpt-3.5-turbo

    references to taking action or the need for action in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cabin
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.66
     Logo
    -0.65
     Fey
    -0.62
     Kou
    -0.62
     Taste
    -0.62
     Beir
    -0.61
     Unic
    -0.61
    ffe
    -0.61
    orf
    -0.61
    POSITIVE LOGITS
     against
    0.98
    able
    0.88
     ACTIONS
    0.83
    ulatory
    0.82
    ivism
    0.81
    fulness
    0.81
    ives
    0.79
     corrective
    0.79
    ional
    0.78
     actions
    0.78
    Act Density 0.052%

    No Known Activations