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

    Neuronpedia

    INDEX
    Explanations

    titles or headings of sections within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohl
    -0.17
    amac
    -0.16
    riad
    -0.16
    اÛĮÛĮ
    -0.15
    irket
    -0.15
    igue
    -0.14
    arga
    -0.14
    acci
    -0.14
    yp
    -0.14
    argins
    -0.14
    POSITIVE LOGITS
    ickerView
    0.15
    freeze
    0.15
    unu
    0.14
     Compass
    0.14
    reator
    0.14
     Norm
    0.14
     neod
    0.14
    edeki
    0.14
    uesta
    0.13
    odon
    0.13
    Act Density 0.007%

    No Known Activations