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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hypothetical situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ¶
    -0.63
    âĢIJ
    -0.63
    Ô
    -0.61
    Comments
    -0.60
    ãģ®ç
    -0.60
    nec
    -0.60
    FIELD
    -0.60
    ÑĮ
    -0.59
    Async
    -0.58
    MENTS
    -0.58
    POSITIVE LOGITS
    mble
    0.84
    ij士
    0.77
    webkit
    0.75
     hypot
    0.73
    isine
    0.72
    asketball
    0.69
    oppers
    0.68
    rell
    0.67
     somehow
    0.65
    hers
    0.64
    Act Density 0.122%

    No Known Activations