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

    Neuronpedia

    INDEX
    Explanations

    specific words related to details or elements of various subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to components or aspects of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dayName
    -0.87
    essors
    -0.78
    redits
    -0.76
    20439
    -0.73
    ricanes
    -0.73
    ħĭ
    -0.71
     Cosponsors
    -0.71
    eches
    -0.69
    odore
    -0.69
    ÅĤ
    -0.67
    POSITIVE LOGITS
     everyday
    0.80
     humanity
    0.76
     warfare
    0.75
     human
    0.72
    processing
    0.70
     life
    0.69
     deprivation
    0.68
     wellness
    0.67
     humankind
    0.66
     Everyday
    0.66
    Act Density 0.115%

    No Known Activations