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

    Neuronpedia

    INDEX
    Explanations

    references to changes in code or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.60
    UserScript
    -0.58
    gonic
    -0.57
    دانشنامهٔ
    -0.52
    UrlResolution
    -0.52
    uxxxx
    -0.52
    principalColumn
    -0.50
    SpringRunner
    -0.49
    ury
    -0.49
    ="#">
    -0.48
    POSITIVE LOGITS
     Diff
    1.10
     diff
    1.07
    diff
    1.04
    Diff
    1.02
     DIFF
    1.00
    DIFF
    0.85
     diffuser
    0.77
     Dif
    0.72
     Difference
    0.71
    diffs
    0.71
    Act Density 0.007%

    No Known Activations