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

    Neuronpedia

    INDEX
    Explanations

    words related to surgical procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to sodomy and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stakes
    -0.71
    itably
    -0.70
    isSpecialOrderable
    -0.69
    UGH
    -0.69
    oice
    -0.68
    qt
    -0.65
    Tu
    -0.64
    ardless
    -0.62
    BILITY
    -0.62
    packing
    -0.62
    POSITIVE LOGITS
    orius
    0.87
    Sov
    0.85
    ell
    0.83
    ales
    0.79
    yre
    0.77
    ella
    0.76
    ells
    0.75
    rett
    0.74
    chester
    0.73
    atio
    0.72
    Act Density 0.032%

    No Known Activations