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

    Neuronpedia

    INDEX
    Explanations

    structural elements of writing or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jur
    -0.14
     shed
    -0.14
    itch
    -0.14
     Vlad
    -0.14
    moduleId
    -0.14
    sem
    -0.14
    nil
    -0.14
    имÑĥ
    -0.13
    ToFit
    -0.13
    urb
    -0.13
    POSITIVE LOGITS
    onas
    0.16
    _skb
    0.15
    CADE
    0.15
    UTE
    0.15
    enor
    0.14
    amarin
    0.14
    lds
    0.14
    eti
    0.14
    _ARROW
    0.14
    Äįka
    0.14
    Act Density 0.001%

    No Known Activations