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

    Neuronpedia

    INDEX
    Explanations

    strong positive adjectives indicative of high quality or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nette
    -0.16
    oko
    -0.16
    duk
    -0.16
    ĥĿ
    -0.15
    ÏĢει
    -0.15
    oleon
    -0.15
    iaux
    -0.15
    oom
    -0.15
    akin
    -0.14
    apper
    -0.14
    POSITIVE LOGITS
    -quality
    0.25
    owl
    0.19
    ly
    0.17
    avery
    0.17
    erate
    0.16
    ordinary
    0.15
    itude
    0.15
    ior
    0.15
     craftsmanship
    0.15
    -value
    0.15
    Act Density 0.026%

    No Known Activations