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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to contexts of organization and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -0.74
    nian
    -0.69
    tie
    -0.69
    ensive
    -0.68
    iques
    -0.66
    icians
    -0.65
    lings
    -0.64
    ians
    -0.64
    nam
    -0.64
    ende
    -0.63
    POSITIVE LOGITS
    VE
    1.48
    UGH
    1.37
    KE
    1.30
    IL
    1.25
    ZE
    1.24
    BILITY
    1.24
    ILS
    1.23
    BLE
    1.22
    HAHA
    1.21
    KER
    1.20
    Act Density 0.109%

    No Known Activations