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

    Neuronpedia

    INDEX
    Explanations

    terms related to accuracy and correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyp
    -0.16
     Reply
    -0.14
    ivol
    -0.13
    etty
    -0.13
    zd
    -0.13
     hypo
    -0.13
    ceph
    -0.13
     ÙħÙĪ
    -0.13
    [edge
    -0.13
     dct
    -0.13
    POSITIVE LOGITS
     late
    0.18
     itself
    0.16
     Late
    0.15
    apons
    0.14
    Late
    0.14
    late
    0.14
     far
    0.14
    å·±
    0.14
     ever
    0.13
    ernet
    0.13
    Act Density 0.015%

    No Known Activations