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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "in" at a high frequency

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

    decline or improvement in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </thead>
    -0.58
     Exactos
    -0.48
    ConstraintMaker
    -0.47
    ględ
    -0.46
    ftagPool
    -0.45
    ésult
    -0.41
    awtextra
    -0.41
     chi̍t
    -0.40
     ModelExpression
    -0.40
     Drapeau
    -0.40
    POSITIVE LOGITS
     pleaſure
    0.43
    Increase
    0.41
     افزایش
    0.41
     повышения
    0.41
    overall
    0.40
     maggiore
    0.40
    posedge
    0.40
     ſen
    0.39
     whofe
    0.39
    Wię
    0.39
    Act Density 0.113%

    No Known Activations