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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and inquiries related to probability and limits

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     performance
    -0.51
     programming
    -0.49
    ]})
    -0.49
    performance
    -0.48
     mengel
    -0.47
     thresholds
    -0.46
    ')")
    -0.46
    "])
    -0.46
    []){
    -0.45
     hierarchy
    -0.45
    POSITIVE LOGITS
    ########.
    0.73
     vertes
    0.65
    SourceChecksum
    0.59
    TagMode
    0.58
    ंदीखरीदारी
    0.56
    UserScript
    0.56
    зулта
    0.56
    Personensuche
    0.55
     GenerationType
    0.54
     Forder
    0.54
    Act Density 0.180%

    No Known Activations