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

    Neuronpedia

    INDEX
    Explanations

    negative coefficients or terms in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nees
    -0.15
    nila
    -0.15
    prox
    -0.15
    icana
    -0.14
    .RowCount
    -0.14
     pride
    -0.14
    apter
    -0.14
    [++
    -0.14
    _PROTO
    -0.13
    ilage
    -0.13
    POSITIVE LOGITS
    лÑİд
    0.18
    .scalablytyped
    0.17
    ditor
    0.15
     Pou
    0.15
    IFn
    0.15
    ezier
    0.15
    antom
    0.14
    üs
    0.14
    iams
    0.14
    ouri
    0.14
    Act Density 0.059%

    No Known Activations