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

    Neuronpedia

    INDEX
    Explanations

    references to physical or conceptual spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trl
    -0.17
    lip
    -0.17
     ÑģкладÑĥ
    -0.16
    rex
    -0.15
    afa
    -0.15
    ross
    -0.15
    thal
    -0.14
    aires
    -0.14
    l
    -0.14
    cul
    -0.14
    POSITIVE LOGITS
    yonel
    0.21
    -temp
    0.18
    /time
    0.18
    yb
    0.16
    holders
    0.15
    flight
    0.15
    bru
    0.15
    ful
    0.15
    uits
    0.15
    -time
    0.14
    Act Density 0.055%

    No Known Activations