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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or confirmations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.72
     Stubbs
    -0.71
    ConstraintLayout
    -0.69
     tru
    -0.68
     BnF
    -0.68
    TRAILING
    -0.65
    WithIOException
    -0.65
     TRUE
    -0.64
    CodeAttribute
    -0.64
    awtextra
    -0.64
    POSITIVE LOGITS
     Yoh
    0.65
     quæ
    0.62
    phyllum
    0.60
     Ähn
    0.58
    WebVitals
    0.56
     Ortschaft
    0.54
     Vedi
    0.54
    teps
    0.53
     meantime
    0.52
    ergies
    0.52
    Act Density 0.004%

    No Known Activations