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

    Neuronpedia

    INDEX
    Explanations

    statistical values and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics related to distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foray
    -0.70
     frontline
    -0.64
     flank
    -0.64
     curfew
    -0.63
    giene
    -0.61
     retrospective
    -0.60
    aging
    -0.60
    rame
    -0.60
     estate
    -0.59
    bara
    -0.59
    POSITIVE LOGITS
    0000000000000000
    1.28
    0000000
    1.27
    000000
    1.25
    %.
    1.21
    $.
    1.19
    9999
    1.19
    00000000
    1.17
    0000
    1.14
     multiplied
    1.13
    /(
    1.10
    Act Density 0.186%

    No Known Activations