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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causes or reasons for an event or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to causes of events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.84
    sonian
    -0.76
    eks
    -0.73
    nets
    -0.72
    Laughs
    -0.72
    Leaks
    -0.70
    ribes
    -0.70
    Pixel
    -0.69
    ellen
    -0.69
    chens
    -0.69
    POSITIVE LOGITS
     displacement
    0.82
     blindness
    0.78
     discrimination
    0.78
     illness
    0.77
     hostilities
    0.74
     miscar
    0.72
     separation
    0.71
     racism
    0.69
     sexism
    0.69
     death
    0.69
    Act Density 0.087%

    No Known Activations