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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming traits and methods

    oai_token-act-pair · gpt-3.5-turbo

    references to specific traits and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.69
    FORE
    -0.69
     ware
    -0.67
    LOAD
    -0.65
    FACE
    -0.64
    pton
    -0.64
    ¹
    -0.63
    ATTLE
    -0.63
    Cod
    -0.63
    apesh
    -0.63
    POSITIVE LOGITS
    ivities
    0.96
    ive
    0.90
    iery
    0.79
    orial
    0.79
    stocks
    0.77
    esse
    0.74
    orship
    0.74
    ously
    0.72
    imus
    0.72
    aired
    0.72
    Act Density 0.106%

    No Known Activations