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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix "ac-" followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to achievement or success in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.93
     Katz
    -0.78
    iday
    -0.74
     Dare
    -0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
     Territories
    -0.69
    ulkan
    -0.69
    éĹĺ
    -0.68
    geist
    -0.68
     Sins
    -0.68
    POSITIVE LOGITS
    robat
    1.17
    oust
    1.08
    rylic
    1.04
    rament
    1.03
    acia
    0.99
    orns
    0.95
    oustic
    0.94
    celer
    0.93
    anth
    0.93
    ros
    0.92
    Act Density 0.010%

    No Known Activations