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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements and technical processes in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lc
    -0.17
    bert
    -0.15
    ovy
    -0.15
    anny
    -0.14
    marshall
    -0.14
    arro
    -0.14
    _INITIALIZER
    -0.14
    æĹıèĩªæ²»
    -0.14
     NONINFRINGEMENT
    -0.14
    lm
    -0.14
    POSITIVE LOGITS
    stru
    0.16
    eworld
    0.16
    Äħd
    0.15
    isser
    0.14
    anyl
    0.14
    obao
    0.14
     Boris
    0.13
     final
    0.13
     alike
    0.13
    _buckets
    0.13
    Act Density 0.154%

    No Known Activations