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

    Neuronpedia

    INDEX
    Explanations

    references to conventional methods or norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     particular
    -0.17
    asons
    -0.17
    ason
    -0.15
    -0.15
    /he
    -0.15
    /th
    -0.14
    uzzi
    -0.14
    ãģŁãĤī
    -0.14
    ³
    -0.14
    ire
    -0.14
    POSITIVE LOGITS
    ists
    0.25
    mente
    0.24
    ism
    0.21
    -looking
    0.20
    ization
    0.20
    istik
    0.19
    ized
    0.19
    -issue
    0.19
    dehyde
    0.19
    ised
    0.19
    Act Density 0.035%

    No Known Activations