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

    Neuronpedia

    INDEX
    Explanations

    words related to buildings, structures, or physical locations

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of being "ed" or "conditioned," often referring to modifications or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kiss
    -0.67
    Story
    -0.64
     derog
    -0.63
     Spears
    -0.63
     Royale
    -0.63
     Aux
    -0.63
     Nun
    -0.63
     Union
    -0.62
     Anthem
    -0.62
     sight
    -0.61
    POSITIVE LOGITS
    ict
    1.14
    ifice
    1.13
    gew
    1.13
    uce
    1.08
    icts
    1.01
    icy
    0.99
    dy
    0.99
    ging
    0.98
    nesday
    0.97
    monton
    0.96
    Act Density 0.013%

    No Known Activations