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

    Neuronpedia

    INDEX
    Explanations

    references to runtime-related activities or configurations

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to software performance and resource management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.90
    osis
    -0.85
    omaly
    -0.85
    awar
    -0.83
    arios
    -0.78
    ionic
    -0.76
    itude
    -0.75
    uman
    -0.74
    essee
    -0.74
    imore
    -0.73
    POSITIVE LOGITS
    framework
    0.72
    susp
    0.71
    ahime
    0.69
    robe
    0.67
    HER
    0.66
    runtime
    0.65
    ptives
    0.64
    endi
    0.63
    jet
    0.63
    ãĤ§
    0.63
    Act Density 0.035%

    No Known Activations