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

    Neuronpedia

    INDEX
    Explanations

    phrases used in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of distinct characters or symbols, particularly in the context of rhetorical or metaphorical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decomp
    -0.78
     JPEG
    -0.75
     Mobil
    -0.64
     pyramid
    -0.63
     Maced
    -0.63
     photoc
    -0.62
     silhou
    -0.62
     scram
    -0.61
     Hats
    -0.61
     decimal
    -0.60
    POSITIVE LOGITS
    s
    1.03
    selves
    1.02
    tal
    0.91
    ski
    0.89
    etimes
    0.88
    forcing
    0.88
    tu
    0.87
    span
    0.87
    science
    0.84
    cause
    0.82
    Act Density 0.241%

    No Known Activations