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

    Neuronpedia

    INDEX
    Explanations

    adjectives that convey qualitative assessments, particularly those indicating positivity or negativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    卿
    -0.51
    stylers
    -0.49
     CanadaChoose
    -0.49
    PT
    -0.49
     incidente
    -0.49
     limón
    -0.48
    marken
    -0.48
    вень
    -0.47
    ?
    -0.47
    期
    -0.47
    POSITIVE LOGITS
    CppMethod
    0.80
    bibfield
    0.76
    styleType
    0.76
    </thead>
    0.73
    PerformLayout
    0.72
    ^(@)
    0.70
    -------------</
    0.69
    зулта
    0.68
    %");
    0.67
    IsContent
    0.67
    Act Density 0.370%

    No Known Activations