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

    Neuronpedia

    INDEX
    Explanations

    terms related to differentiation or differences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å²³
    -0.17
    ocs
    -0.17
     liá»ĩu
    -0.17
    anism
    -0.17
    ebra
    -0.16
    IVEN
    -0.16
    figcaption
    -0.15
    pine
    -0.15
    eer
    -0.15
    tul
    -0.15
    POSITIVE LOGITS
    icult
    0.28
    usion
    0.24
    rence
    0.21
    ussion
    0.20
    raction
    0.20
    usive
    0.18
     Diff
    0.17
     b
    0.17
     diff
    0.17
    .Diff
    0.17
    Act Density 0.012%

    No Known Activations