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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating probability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iken
    -0.15
     оÑĩ
    -0.14
    vider
    -0.14
    á»į
    -0.13
     terse
    -0.13
    eki
    -0.13
    маз
    -0.13
    Gatt
    -0.13
    __;
    -0.13
     ÑĩаÑģ
    -0.12
    POSITIVE LOGITS
     precisely
    0.17
     somebody
    0.15
    398
    0.15
    ARB
    0.15
     far
    0.15
     exactly
    0.14
    igham
    0.14
    ozem
    0.14
    arian
    0.14
    |↵↵
    0.14
    Act Density 0.000%

    No Known Activations