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

    prominent names and entities involved in notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereof
    -0.76
    .</
    -0.75
    }.
    -0.71
    .).
    -0.71
     ..."
    -0.70
    ".[
    -0.70
    $.
    -0.69
    ]."
    -0.68
     etc
    -0.67
    )."
    -0.66
    POSITIVE LOGITS
     meanwhile
    0.86
    ccording
    0.63
     spokesman
    0.61
     spokeswoman
    0.60
     Lavrov
    0.60
    odore
    0.59
    resa
    0.58
    surprisingly
    0.57
    ':
    0.56
     Lauder
    0.55
    Act Density 2.794%

    No Known Activations