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

    Neuronpedia

    INDEX
    Explanations

    terms related to construction and efficiency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cko
    -0.16
    izzo
    -0.16
    sov
    -0.15
    iteli
    -0.15
    ogi
    -0.14
    Ghost
    -0.14
    ucas
    -0.14
     Belediyesi
    -0.14
    uche
    -0.14
    otal
    -0.13
    POSITIVE LOGITS
     options
    0.18
     Options
    0.17
    atori
    0.16
    options
    0.15
    .soft
    0.15
    Options
    0.15
     methods
    0.15
    -options
    0.15
    rst
    0.15
    anyl
    0.14
    Act Density 0.398%

    No Known Activations