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

    Neuronpedia

    INDEX
    Explanations

    phrases related to classroom activities and settings

    oai_token-act-pair · gpt-3.5-turbo

    references to academic classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.71
     Bay
    -0.66
     porous
    -0.66
    vernment
    -0.65
     viral
    -0.63
     mutated
    -0.62
    cean
    -0.61
     wrench
    -0.61
     amplified
    -0.59
     arresting
    -0.58
    POSITIVE LOGITS
    ifications
    1.03
    room
    0.97
    ifiers
    0.95
    ifier
    0.91
    anova
    0.91
    ifies
    0.87
    girl
    0.85
    girls
    0.84
    rooms
    0.83
     lessons
    0.82
    Act Density 0.027%

    No Known Activations