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

    Neuronpedia

    INDEX
    Explanations

    official or organizational bodies, institutions, or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or bodies with governmental or authoritative roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hoover
    -0.69
    kers
    -0.68
     Dickens
    -0.66
    é¾į
    -0.65
     Jarrett
    -0.64
    icago
    -0.64
     Doodle
    -0.63
    edia
    -0.63
     Kafka
    -0.61
     Prescott
    -0.60
    POSITIVE LOGITS
    weight
    0.96
    building
    0.95
     politic
    0.94
    guards
    0.94
    builders
    0.89
    chair
    0.88
    member
    0.84
    builder
    0.80
    guard
    0.78
    weights
    0.76
    Act Density 0.019%

    No Known Activations