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

    Neuronpedia

    INDEX
    Explanations

    words related to system dependencies, financial terms, and governance structures

    oai_token-act-pair · gpt-3.5-turbo

    topics related to dependencies and influences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.56
    Else
    -0.53
    BUG
    -0.52
    Ott
    -0.52
    OUS
    -0.52
    ãĤ¨ãĥ«
    -0.51
    oÄŁ
    -0.48
     Hat
    -0.48
    same
    -0.47
    LESS
    -0.45
    POSITIVE LOGITS
    hips
    1.13
    hip
    1.04
    paces
    1.03
    pace
    0.97
    poons
    0.95
    hops
    0.94
    mith
    0.91
    ynthesis
    0.88
    uggest
    0.87
    pring
    0.87
    Act Density 0.776%

    No Known Activations