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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of disbelief or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shell
    -0.14
    vid
    -0.14
    /rfc
    -0.14
    åħ¹
    -0.14
     Vega
    -0.14
    /goto
    -0.14
    tlement
    -0.14
    \Message
    -0.13
    اÙĤ
    -0.13
    iv
    -0.13
    POSITIVE LOGITS
    otel
    0.17
     circum
    0.17
    hte
    0.15
    upal
    0.14
     Kel
    0.14
    nicas
    0.14
    _ASSUME
    0.14
    รร
    0.14
    adlo
    0.14
    ruž
    0.14
    Act Density 0.169%

    No Known Activations