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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and identifiers related to lists or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    166
    -0.17
     cat
    -0.17
    ash
    -0.16
    ritt
    -0.16
     ash
    -0.15
    ¼
    -0.15
    peri
    -0.15
     Kitchen
    -0.14
    jit
    -0.14
     Hammond
    -0.14
    POSITIVE LOGITS
    mares
    0.16
    Injector
    0.15
    ãĥ¥
    0.15
    quo
    0.15
    ieval
    0.15
    avras
    0.15
    ROKE
    0.15
    ãĤ¡
    0.14
    roll
    0.14
    roke
    0.14
    Act Density 0.031%

    No Known Activations