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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intention, planning, and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    instances of intention or purpose in actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¼
    -0.64
    Recently
    -0.63
    /
    -0.63
    ________________________________________________________________
    -0.61
    --------------------
    -0.60
     thats
    -0.60
    âĿ
    -0.60
    #$#$
    -0.59
    umat
    -0.58
    [/
    -0.57
    POSITIVE LOGITS
     chiefly
    0.86
     merely
    0.77
     instead
    0.72
     principally
    0.69
     rather
    0.69
     to
    0.68
     unspecified
    0.67
     primarily
    0.67
     mainly
    0.66
     narrower
    0.65
    Act Density 0.810%

    No Known Activations