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

    Neuronpedia

    INDEX
    Explanations

    similes comparing actions to physical force or movement

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or similes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilic
    -0.79
    inion
    -0.76
    byn
    -0.76
    ysical
    -0.75
    elin
    -0.74
    inas
    -0.74
    hiba
    -0.73
    hani
    -0.73
    iets
    -0.72
    Published
    -0.72
    POSITIVE LOGITS
    lihood
    1.17
    lier
    1.02
    liest
    0.97
     wildfire
    0.89
     clock
    0.84
     crazy
    0.84
    liness
    0.80
     minded
    0.73
     mad
    0.72
     idiots
    0.72
    Act Density 0.063%

    No Known Activations