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

    Neuronpedia

    INDEX
    Explanations

    mathematical derivatives and partial differential terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+
    -0.74
    
    -0.73
     CommonModule
    -0.71
    Personensuche
    -0.70
    ntax
    -0.65
    thyst
    -0.65
     Himo
    -0.65
    Agencia
    -0.65
    minaire
    -0.65
    ("")]
    -0.64
    POSITIVE LOGITS
    SL
    0.50
    клопе
    0.50
    uri
    0.48
    9
    0.47
     Optimum
    0.47
     professionale
    0.46
    S
    0.46
    ris
    0.46
     anbef
    0.46
     peep
    0.45
    Act Density 0.015%

    No Known Activations