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

    Neuronpedia

    INDEX
    Explanations

    code comments starting with "How many bits" followed by code-related tokens

    oai_token-act-pair · gpt-3.5-turbo

    instances of high stress or urgency in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    binary
    -0.77
    rad
    -0.73
    ction
    -0.72
    mbuds
    -0.70
    isons
    -0.68
    ussian
    -0.65
    abouts
    -0.63
    dit
    -0.62
    nor
    -0.61
    altern
    -0.61
    POSITIVE LOGITS
    ³³³
    0.88
    ³³³³³³³³³³³³³³³³
    0.75
    ³³³³
    0.75
     ante
    0.70
     Emanuel
    0.67
    ³³³³³³³³
    0.63
    âĵĺ
    0.61
     HA
    0.60
     Tribune
    0.58
    é¾
    0.58
    Act Density 0.479%

    No Known Activations