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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    events or dates related to significant occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     previous
    -0.60
     latter
    -0.59
     positives
    -0.57
     initially
    -0.56
     stances
    -0.55
     notable
    -0.55
     reconc
    -0.54
    okingly
    -0.54
     earlier
    -0.53
    sequently
    -0.53
    POSITIVE LOGITS
     goddamn
    0.79
    âĢ
    0.76
    "—
    0.74
    ——
    0.74
     ..."
    0.70
    .''
    0.69
    —-
    0.69
    !'"
    0.69
    !!"
    0.69
     trillions
    0.68
    Act Density 1.253%

    No Known Activations