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

    Neuronpedia

    INDEX
    Explanations

    grammatically structured phrases with specific keyword patterns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osaurus
    -0.76
    nikov
    -0.72
    facing
    -0.66
    essing
    -0.66
    oi
    -0.62
    rait
    -0.61
    ocene
    -0.59
    wage
    -0.58
     Frie
    -0.58
    ulla
    -0.58
    POSITIVE LOGITS
     disbanded
    0.78
    senal
    0.76
     charter
    0.72
     acronym
    0.71
    ADRA
    0.69
    lishes
    0.69
    ITION
    0.68
    exempt
    0.68
    LET
    0.67
     disband
    0.67
    Act Density 0.428%

    No Known Activations