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

    Neuronpedia

    INDEX
    Explanations

    references to documentation and processes related to data management and verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abort
    -0.19
    Generated
    -0.19
     concaten
    -0.18
     applaud
    -0.17
     trunc
    -0.17
    utra
    -0.17
    woke
    -0.16
     intercept
    -0.16
     embed
    -0.16
     dispatch
    -0.16
    POSITIVE LOGITS
     thrown
    0.23
     placed
    0.22
     taken
    0.22
     photographed
    0.21
     distributed
    0.21
     transferred
    0.20
     handed
    0.20
     flown
    0.20
     kept
    0.20
     transported
    0.20
    Act Density 0.237%

    No Known Activations