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

    Neuronpedia

    INDEX
    Explanations

    inquiries about reasoning or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    าศ
    -0.16
    kn
    -0.16
    iš
    -0.15
    phan
    -0.15
    adesh
    -0.14
    otate
    -0.14
    uš
    -0.14
    gs
    -0.14
    tera
    -0.14
    ibri
    -0.14
    POSITIVE LOGITS
    ?
    0.18
    earch
    0.18
    ëĥIJ
    0.15
     ello
    0.15
     esto
    0.15
    637
    0.15
    ippers
    0.15
    ernals
    0.14
    ENTS
    0.14
    eca
    0.14
    Act Density 0.062%

    No Known Activations