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

    Neuronpedia

    INDEX
    Explanations

    discussions and references to arguments or debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eler
    -0.16
    ties
    -0.16
    ikut
    -0.16
    igan
    -0.15
    igans
    -0.15
     rack
    -0.15
    esters
    -0.15
    vez
    -0.15
    appropri
    -0.14
    ustum
    -0.14
    POSITIVE LOGITS
    ative
    0.28
    uably
    0.23
    UMENT
    0.22
    atively
    0.20
    ÑĥменÑĤ
    0.19
    inine
    0.18
    OutOfRangeException
    0.18
    against
    0.17
    yle
    0.17
    YLE
    0.17
    Act Density 0.032%

    No Known Activations