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

    Neuronpedia

    INDEX
    Explanations

    conditional or hypothetical statements and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peak
    -0.18
     Peak
    -0.16
    748
    -0.15
     Intr
    -0.15
    ekil
    -0.14
    ovie
    -0.14
    decorate
    -0.14
    i
    -0.14
    âĶĥ
    -0.14
    Peak
    -0.14
    POSITIVE LOGITS
    mdir
    0.15
    ạm
    0.15
    ScreenState
    0.14
    _fa
    0.14
    cke
    0.14
    erg
    0.14
    лев
    0.14
    ãģıãĤĵ
    0.14
    Seeder
    0.13
    peq
    0.13
    Act Density 0.002%

    No Known Activations