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

    Neuronpedia

    INDEX
    Explanations

    acronyms or initialisms with high importance

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations that signify organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cerberus
    -0.82
     fame
    -0.67
     guarding
    -0.66
     Highlands
    -0.66
     basket
    -0.63
     Fundamental
    -0.62
     Founders
    -0.62
     Goddess
    -0.60
     swinging
    -0.60
     trans
    -0.60
    POSITIVE LOGITS
    mosp
    0.90
    theless
    0.86
    ogether
    0.84
    NetMessage
    0.77
    agascar
    0.77
    idav
    0.76
    endum
    0.76
    oby
    0.75
    uador
    0.75
    etheless
    0.74
    Act Density 0.287%

    No Known Activations