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

    Neuronpedia

    INDEX
    Explanations

    various types of categories or classifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating variety or multiple categories of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heid
    -0.81
    LAN
    -0.74
    edia
    -0.71
    adium
    -0.70
    Recomm
    -0.68
    hani
    -0.67
    Interstitial
    -0.66
    mented
    -0.66
    mary
    -0.66
    aeper
    -0.66
    POSITIVE LOGITS
    etter
    0.92
    hots
    0.81
    chool
    0.79
    paces
    0.77
    pace
    0.76
    etting
    0.76
    afe
    0.73
    ucker
    0.70
    cue
    0.66
    ãĥĺ
    0.66
    Act Density 0.016%

    No Known Activations