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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons or contrasts between different options or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    太éĥİ
    -0.17
    uen
    -0.15
    ochen
    -0.15
    SharedPointer
    -0.14
    afort
    -0.14
    arn
    -0.14
    stroy
    -0.14
    enic
    -0.14
    msg
    -0.13
     amy
    -0.13
    POSITIVE LOGITS
    iyim
    0.17
    dül
    0.16
    653
    0.16
    oner
    0.16
    934
    0.15
    ilos
    0.15
    poz
    0.14
    ritis
    0.14
    thr
    0.14
     Vere
    0.14
    Act Density 0.029%

    No Known Activations