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

    Neuronpedia

    INDEX
    Explanations

    references to proposals or suggestions for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    een
    -0.18
    liness
    -0.17
    uous
    -0.16
    nes
    -0.15
    lify
    -0.15
    aylor
    -0.15
    ÑĢак
    -0.15
    noop
    -0.15
     nhau
    -0.15
    ëĿ½
    -0.15
    POSITIVE LOGITS
    ÑģÑĮ
    0.18
    entially
    0.17
    اتÛĮ
    0.17
    /request
    0.17
    itional
    0.17
    able
    0.15
    ive
    0.15
    ively
    0.15
    ãĥ£
    0.15
    hoot
    0.15
    Act Density 0.041%

    No Known Activations