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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning something as being a section or component of a larger entity or concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate participation or involvement in various activities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.71
     ceilings
    -0.68
    intent
    -0.66
    20439
    -0.66
    apons
    -0.65
    anches
    -0.64
    stasy
    -0.64
    ricanes
    -0.63
    berus
    -0.63
    olesc
    -0.61
    POSITIVE LOGITS
    ially
    0.94
    aking
    0.83
    ioned
    0.78
    ners
    0.77
    icularly
    0.77
    nered
    0.75
    heartedly
    0.74
    ials
    0.74
    seless
    0.72
    meal
    0.72
    Act Density 0.036%

    No Known Activations