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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to evaluations and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lep
    -0.16
     Hermes
    -0.15
    ui
    -0.15
     Gwen
    -0.14
    rette
    -0.14
    903
    -0.14
     Gaul
    -0.13
     ch
    -0.13
    ikel
    -0.13
    037
    -0.13
    POSITIVE LOGITS
    orton
    0.16
    ruptcy
    0.15
    oppable
    0.15
    hall
    0.15
    udit
    0.14
     ifndef
    0.14
    nas
    0.14
    crc
    0.14
     ifdef
    0.13
    Force
    0.13
    Act Density 0.056%

    No Known Activations