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

    Neuronpedia

    INDEX
    Explanations

    summary statements or sections indicating conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.85
    en
    -0.79
    u
    -0.76
    in
    -0.72
    o
    -0.72
    ik
    -0.71
    y
    -0.70
    bø
    -0.70
    an
    -0.69
    et
    -0.69
    POSITIVE LOGITS
    OVERALL
    1.40
    RectangleBorder
    1.33
    ſelves
    1.31
     contextLoads
    1.30
    MigrationBuilder
    1.26
    ſelf
    1.26
    LookAnd
    1.22
     itſelf
    1.19
     myſelf
    1.15
    Personendaten
    1.13
    Act Density 0.073%

    No Known Activations