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

    Neuronpedia

    INDEX
    Explanations

    references to prestigious literary awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ole
    -0.18
    ERS
    -0.16
    ers
    -0.16
    lder
    -0.15
    olate
    -0.15
    γ
    -0.15
    ippers
    -0.14
    chan
    -0.14
     Acad
    -0.14
    brook
    -0.14
    POSITIVE LOGITS
    ahn
    0.16
    ozo
    0.15
    ança
    0.15
     unlucky
    0.15
    lotte
    0.14
    cade
    0.14
    weets
    0.14
    ecycle
    0.13
     Daemon
    0.13
    моÑĤ
    0.13
    Act Density 0.001%

    No Known Activations