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

    Neuronpedia

    INDEX
    Explanations

    references to particular people or personalities

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "people like" to discuss opinions or characteristics of certain individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.73
    ahime
    -0.73
    erial
    -0.72
    ilogy
    -0.71
    FORMATION
    -0.70
    ourse
    -0.70
    ipple
    -0.70
    iven
    -0.69
    arbon
    -0.69
    atform
    -0.69
    POSITIVE LOGITS
    lier
    1.10
    lihood
    1.08
     yours
    0.89
     Mike
    0.85
    liest
    0.84
     Geoff
    0.84
     Amir
    0.83
    pires
    0.83
     Pamela
    0.83
     Erik
    0.82
    Act Density 0.104%

    No Known Activations