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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of inability or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hen
    -0.17
    èĥ½
    -0.16
    geh
    -0.14
    ively
    -0.13
    had
    -0.13
     olmayan
    -0.13
    ally
    -0.13
    orge
    -0.13
    entially
    -0.13
    rote
    -0.13
    POSITIVE LOGITS
    ches
    0.19
     necessarily
    0.19
    berra
    0.17
    ched
    0.17
    ching
    0.17
    oriously
    0.17
    AccessException
    0.16
    epad
    0.16
    /w
    0.15
    rzy
    0.15
    Act Density 0.047%

    No Known Activations