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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uld
    -0.64
    matter
    -0.62
    Fuck
    -0.61
    âĶĢâĶĢ
    -0.60
    alien
    -0.58
     phases
    -0.58
    uggle
    -0.58
    itized
    -0.58
    Higher
    -0.58
     Golem
    -0.58
    POSITIVE LOGITS
    enegger
    1.01
     reportedly
    0.81
     photographed
    0.77
    anwhile
    0.77
     quoted
    0.76
     himself
    0.75
     famously
    0.74
    ersen
    0.73
     pictured
    0.73
    */(
    0.72
    Act Density 0.385%

    No Known Activations