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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comparison and outcome states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.50
     fieldNum
    -0.41
     purpoſe
    -0.41
    zeitig
    -0.40
     يتيمه
    -0.40
    jalá
    -0.38
    Personendaten
    -0.38
    舺
    -0.38
     estekak
    -0.37
     avoient
    -0.37
    POSITIVE LOGITS
     StringTokenizer
    0.56
    CloseOperation
    0.46
    Worse
    0.46
     fared
    0.45
     similarly
    0.42
     Worse
    0.41
    UrlResolution
    0.41
     ModelExpression
    0.40
     betweenstory
    0.39
    windowFixed
    0.39
    Act Density 0.183%

    No Known Activations