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

    Neuronpedia

    INDEX
    Explanations

    propper nouns and specific phrases related to various titles and names

    oai_token-act-pair · gpt-3.5-turbo

    the character 'ľ' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     condem
    -0.97
     disadvant
    -0.81
     appropri
    -0.78
     simultane
    -0.76
     conduc
    -0.75
     reflex
    -0.74
     lapse
    -0.73
     apes
    -0.72
     assum
    -0.72
    enegger
    -0.72
    POSITIVE LOGITS
    ï¸ı
    1.08
    cffffcc
    1.00
    ICE
    0.98
    lean
    0.89
    Sing
    0.87
    VAL
    0.86
    XY
    0.86
    ternity
    0.86
    Operation
    0.86
    active
    0.85
    Act Density 0.208%

    No Known Activations