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

    Neuronpedia

    INDEX
    Explanations

    instances of parenthetical statements or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Invariant
    -0.14
     Extract
    -0.14
    aine
    -0.14
    eldom
    -0.14
    éĩ
    -0.14
    uther
    -0.14
    \xff
    -0.13
    YPRE
    -0.13
    trl
    -0.13
    amework
    -0.13
    POSITIVE LOGITS
    AdapterFactory
    0.17
    iver
    0.15
    oble
    0.14
    858
    0.14
    ssel
    0.14
    owski
    0.13
    Lorem
    0.13
    icer
    0.13
    ëŀij
    0.13
    ool
    0.13
    Act Density 0.095%

    No Known Activations