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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures in complex lists or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onas
    -0.17
    ARGIN
    -0.16
    Margins
    -0.15
    ovit
    -0.13
    chs
    -0.12
    ingu
    -0.12
    hazi
    -0.12
    bett
    -0.12
     oÄŁ
    -0.12
    odied
    -0.12
    POSITIVE LOGITS
     nuest
    0.14
    jsonp
    0.13
    Ìī
    0.13
    Destructor
    0.13
    eyJ
    0.13
    .LoggerFactory
    0.13
    æ±Ĺ
    0.13
    utan
    0.13
     downright
    0.12
    spor
    0.12
    Act Density 0.143%

    No Known Activations