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

    Neuronpedia

    INDEX
    Explanations

    words related to the perpetuation of certain beliefs or actions

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb that relate to sustaining or maintaining something negative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eaten
    -0.64
     recovered
    -0.64
     tam
    -0.62
    acked
    -0.62
     mol
    -0.61
     drunk
    -0.61
     christ
    -0.61
     monster
    -0.60
     mutated
    -0.60
     rampage
    -0.59
    POSITIVE LOGITS
    uating
    3.89
    uates
    3.88
    uate
    3.59
    uations
    2.33
    uation
    2.11
    uated
    2.03
    uum
    1.40
    ually
    1.19
    uing
    1.17
    ual
    1.02
    Act Density 0.020%

    No Known Activations