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

    Neuronpedia

    INDEX
    Explanations

    information related to ordering, shipping, and instructions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to events or notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fleeing
    -0.81
     alive
    -0.76
     escaping
    -0.76
     dubbed
    -0.76
     herself
    -0.75
     sustained
    -0.74
     tackling
    -0.74
     feared
    -0.73
     cuts
    -0.72
     potent
    -0.72
    POSITIVE LOGITS
    If
    1.30
    --------------------------------------------------------
    1.27
    NOTE
    1.26
    Disclaimer
    1.25
    Example
    1.25
    Please
    1.25
    Examples
    1.25
    Click
    1.24
    FAQ
    1.24
    Download
    1.24
    Act Density 0.498%

    No Known Activations