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

    Neuronpedia

    INDEX
    Explanations

    statements or proposals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating that something is being stated or asserted

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geist
    -0.72
    ACP
    -0.71
    cop
    -0.71
    ski
    -0.68
    boot
    -0.68
    dt
    -0.65
    Web
    -0.64
    control
    -0.64
    cano
    -0.64
    croft
    -0.64
    POSITIVE LOGITS
    irection
    0.83
    LY
    0.74
    edge
    0.72
     hypocr
    0.70
    oaded
    0.69
    ivable
    0.68
    redients
    0.67
     aloud
    0.65
    ixel
    0.64
    ļé
    0.64
    Act Density 0.093%

    No Known Activations