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

    Neuronpedia

    INDEX
    Explanations

    sections of academic or technical citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zyst
    -0.16
    ece
    -0.16
    geç
    -0.14
    stag
    -0.14
    _epi
    -0.14
    criptor
    -0.14
    ControlItem
    -0.14
    habi
    -0.14
    rics
    -0.14
    ales
    -0.14
    POSITIVE LOGITS
     redd
    0.21
     Feast
    0.21
    /catalog
    0.19
     Subaru
    0.19
     faint
    0.18
     fid
    0.18
     GOODS
    0.17
     instrumental
    0.17
    âĺħ
    0.17
    .fits
    0.17
    Act Density 0.115%

    No Known Activations