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

    Neuronpedia

    INDEX
    Explanations

    instances where something is explicitly specified or defined

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "specifying" and "specificity."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilee
    -0.78
    Pear
    -0.78
    stra
    -0.73
    tip
    -0.73
    Īè
    -0.72
    spot
    -0.72
    anch
    -0.72
    beat
    -0.72
    be
    -0.71
    IU
    -0.70
    POSITIVE LOGITS
     specifications
    0.88
     wording
    0.86
     thresholds
    0.85
     parameters
    0.84
     criteria
    0.84
     labels
    0.79
    wcsstore
    0.76
     explicitly
    0.75
     deadlines
    0.73
    imen
    0.73
    Act Density 0.031%

    No Known Activations