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

    Neuronpedia

    INDEX
    Explanations

    words related to physical structures and equipment

    oai_token-act-pair · gpt-3.5-turbo

    various objects, tools, or components related to construction and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -0.85
    ãĥį
    -0.81
    âĸ¬
    -0.81
    76561
    -0.76
    oÄŁ
    -0.68
    ãĥ¯ãĥ³
    -0.66
    ãĥĥãĥī
    -0.64
    stream
    -0.64
    é¾įå
    -0.64
    à©
    -0.63
    POSITIVE LOGITS
    hips
    1.47
    poons
    1.29
    hip
    1.18
    uits
    1.13
    mith
    1.12
    uggest
    1.08
    hops
    1.06
    etting
    1.03
    ynthesis
    1.01
    paces
    1.00
    Act Density 0.510%

    No Known Activations