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

    Neuronpedia

    INDEX
    Explanations

    linguistic elements and expressions in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pel
    -0.19
    ÏĥÏĢ
    -0.15
    caled
    -0.15
    conduct
    -0.15
    zung
    -0.14
    ensex
    -0.14
    rane
    -0.14
    imentos
    -0.14
    ropol
    -0.14
    celed
    -0.14
    POSITIVE LOGITS
    acho
    0.17
    tal
    0.16
    977
    0.16
    aÄį
    0.15
    877
    0.15
    106
    0.14
    tol
    0.14
     synthesis
    0.14
    xin
    0.14
    886
    0.13
    Act Density 0.013%

    No Known Activations