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

    Neuronpedia

    INDEX
    Explanations

    words that convey a sense of conclusion or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.18
     however
    -0.17
    ense
    -0.16
    ensen
    -0.15
     or
    -0.14
    ties
    -0.14
    ilos
    -0.14
    tre
    -0.14
    ensed
    -0.14
    _IO
    -0.13
    POSITIVE LOGITS
    ebek
    0.15
    etak
    0.15
    uebas
    0.14
    usses
    0.14
    /OR
    0.13
    ibr
    0.13
    stuff
    0.13
    ime
    0.13
    IME
    0.13
    stinence
    0.13
    Act Density 0.178%

    No Known Activations