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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures/entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people, places, or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )."
    -0.45
    ]."
    -0.45
    ).[
    -0.42
    )).
    -0.41
    ".[
    -0.40
    .'"
    -0.38
    .''.
    -0.38
    ]).
    -0.37
    catentry
    -0.37
    '."
    -0.36
    POSITIVE LOGITS
    ogie
    0.41
    ragon
    0.34
     haircut
    0.34
     hen
    0.33
     cruising
    0.32
    lycer
    0.32
    ucker
    0.32
    cients
    0.32
    apeshifter
    0.31
    ahime
    0.30
    Act Density 4.668%

    No Known Activations