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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, regulations, and processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to character development in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    was
    -0.67
     remembers
    -0.65
    laughs
    -0.65
    Its
    -0.64
     loses
    -0.63
     sleeps
    -0.63
     prefers
    -0.62
     blames
    -0.62
     thinks
    -0.62
     Goes
    -0.62
    POSITIVE LOGITS
     themselves
    1.19
     respectively
    1.13
     collectively
    1.04
     individually
    0.94
     respective
    0.92
     varying
    0.82
     constitute
    0.82
    geries
    0.80
    selves
    0.79
     together
    0.79
    Act Density 0.862%

    No Known Activations