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

    Neuronpedia

    INDEX
    Explanations

    evaluations of value and quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chaft
    -0.15
    aname
    -0.15
    verbs
    -0.14
    lings
    -0.14
    asan
    -0.14
    ãĥ¼ãĥ
    -0.14
     Ort
    -0.14
     Friedman
    -0.13
    scoped
    -0.13
     bluff
    -0.13
    POSITIVE LOGITS
    mi
    0.17
    -middle
    0.14
    yal
    0.14
    ogra
    0.14
    Ïįν
    0.14
     noch
    0.14
    ewhat
    0.14
    ä½Ĩæĺ¯
    0.13
    ild
    0.13
    edla
    0.13
    Act Density 0.203%

    No Known Activations