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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news events

    oai_token-act-pair · gpt-3.5-turbo

    the word "Just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.75
    existent
    -0.66
    senal
    -0.62
    der
    -0.60
     thereof
    -0.59
     Prelude
    -0.58
     conflic
    -0.58
    lled
    -0.57
     challeng
    -0.57
     pupil
    -0.57
    POSITIVE LOGITS
    ices
    1.10
    ifications
    1.06
     kidding
    1.00
    itia
    0.98
    ifiable
    0.94
    icia
    0.93
    ification
    0.92
    ified
    0.89
    ifi
    0.88
    if
    0.84
    Act Density 0.050%

    No Known Activations