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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental results in scientific studies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.94
    ✨:
    -0.81
    ://"
    -0.81
    "]}
    -0.81
     Meksiku
    -0.79
    halb
    -0.78
    __":
    -0.78
    __":
    -0.77
    __':
    -0.77
    -------------</
    -0.76
    POSITIVE LOGITS
    ness
    0.73
    s
    0.71
    n
    0.64
     Fiske
    0.63
    Arne
    0.62
    Deviation
    0.61
    WithType
    0.60
     Macdonald
    0.60
    ési
    0.59
    tieth
    0.59
    Act Density 0.037%

    No Known Activations