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

    Neuronpedia

    INDEX
    Explanations

    parentheses and mathematical symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.86
    Бахар
    -0.84
     nakalista
    -0.80
    tonsoft
    -0.69
    setVerticalGroup
    -0.66
     numberOfRows
    -0.65
     CanadaChoose
    -0.65
     tartalomajánló
    -0.64
     cherchés
    -0.63
     Tiber
    -0.63
    POSITIVE LOGITS
    coque
    0.50
     kör
    0.50
     integrity
    0.49
     knowledge
    0.46
    koe
    0.46
    matchCondition
    0.45
    Knock
    0.45
     gesamte
    0.45
    性和
    0.44
    ########.
    0.44
    Act Density 0.024%

    No Known Activations