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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making or planning

    oai_token-act-pair · gpt-3.5-turbo

    frequent expressions of certainty and ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bia
    -0.69
     CLSID
    -0.63
    cheon
    -0.62
    bourg
    -0.61
    >>\
    -0.60
     presently
    -0.60
    ·
    -0.60
    adobe
    -0.59
    »Ĵ
    -0.58
    VICE
    -0.57
    POSITIVE LOGITS
    ounters
    0.71
    ailable
    0.70
    rences
    0.68
    ãĤ£
    0.66
    ministic
    0.65
    enos
    0.64
    hyde
    0.64
    onen
    0.64
    brates
    0.63
     Nights
    0.63
    Act Density 0.249%

    No Known Activations