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

    Neuronpedia

    INDEX
    Explanations

    negative assertions and phrases indicating a lack of validity or seriousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourt
    -0.17
    mant
    -0.15
    inux
    -0.15
    shaw
    -0.15
    91
    -0.14
    ÑĩаÑĤ
    -0.14
    usz
    -0.14
    Ùħد
    -0.14
    _mgr
    -0.13
    ÑĢовод
    -0.13
    POSITIVE LOGITS
    ched
    0.17
     anymore
    0.17
    iced
    0.15
    ching
    0.15
    endez
    0.15
    iglia
    0.15
    å¤Ł
    0.14
    کرÛĮ
    0.14
    oriously
    0.14
    ori
    0.14
    Act Density 0.041%

    No Known Activations