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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic studies or topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.77
    earchers
    -0.67
    wall
    -0.67
    cedented
    -0.67
    ħĭ
    -0.66
     [&
    -0.65
    DragonMagazine
    -0.65
    ername
    -0.63
    fal
    -0.63
     jaws
    -0.63
    POSITIVE LOGITS
     warfare
    0.86
     Warfare
    0.80
    version
    0.76
    effic
    0.74
    heres
    0.73
     Ruin
    0.70
    each
    0.69
    efficiency
    0.66
    icial
    0.64
     course
    0.63
    Act Density 0.209%

    No Known Activations