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

    Neuronpedia

    INDEX
    Explanations

    words related to non-conformity or forms of resistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "form" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spree
    -0.67
    EStream
    -0.62
     Royals
    -0.62
     breath
    -0.60
     Seas
    -0.58
     simmer
    -0.58
     cart
    -0.58
    EStreamFrame
    -0.57
     FML
    -0.57
    mine
    -0.56
    POSITIVE LOGITS
    idable
    1.30
    atted
    1.24
    aldehyde
    1.18
    ulations
    1.12
    ational
    1.11
    ulation
    1.02
    ula
    0.99
    ative
    0.98
    ulate
    0.97
    ations
    0.96
    Act Density 0.022%

    No Known Activations