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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong opinions or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stad
    -0.16
    antor
    -0.15
    .openg
    -0.15
    ainers
    -0.15
    μÏĢο
    -0.14
    463
    -0.14
     Chain
    -0.13
    èĨ
    -0.13
    äft
    -0.13
    ãģ°ãģĭãĤĬ
    -0.13
    POSITIVE LOGITS
    nul
    0.16
    anik
    0.15
    xffffff
    0.15
    atra
    0.14
    uyen
    0.14
    758
    0.14
    tele
    0.14
    asy
    0.14
    RIPT
    0.13
    agon
    0.13
    Act Density 0.041%

    No Known Activations