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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity and desire for information or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stras
    -0.17
    swire
    -0.17
     Sesso
    -0.15
    cljs
    -0.15
    ICIENT
    -0.15
    iams
    -0.14
    ÅĻen
    -0.14
    éric
    -0.14
     ÄĮech
    -0.14
     zel
    -0.14
    POSITIVE LOGITS
    ?
    0.23
     yourself
    0.17
    ?↵
    0.15
    ØŁ
    0.15
    «
    0.14
    @
    0.14
    um
    0.14
     æĽ´
    0.14
    StateException
    0.14
    ãģ§ãģĻãģĭ
    0.13
    Act Density 0.032%

    No Known Activations