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

    Neuronpedia

    INDEX
    Explanations

    strong emphasis on words within apostrophes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the apostrophe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -0.59
    asma
    -0.59
    manship
    -0.58
     reconciliation
    -0.58
     Pru
    -0.57
     answ
    -0.57
     fundamentals
    -0.57
    asing
    -0.56
    İĭ
    -0.55
     bonds
    -0.55
    POSITIVE LOGITS
    Cause
    0.97
    Allah
    0.89
    Mech
    0.78
    Em
    0.77
    S
    0.77
    Angelo
    0.72
    ead
    0.72
    Brien
    0.72
    thur
    0.71
    uese
    0.71
    Act Density 0.046%

    No Known Activations