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

    Neuronpedia

    INDEX
    Explanations

    names containing the pattern "ane" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cane" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.85
    rador
    -0.75
    spring
    -0.72
    sburgh
    -0.71
    dogs
    -0.69
    andise
    -0.67
    lishes
    -0.66
    said
    -0.66
    achusetts
    -0.64
    orate
    -0.64
    POSITIVE LOGITS
    hyde
    1.08
    jad
    0.95
    cki
    0.94
    gas
    0.91
    cker
    0.82
    agle
    0.82
    ck
    0.81
    vil
    0.79
    resp
    0.78
    utral
    0.78
    Act Density 0.075%

    No Known Activations