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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    486
    -0.17
    ÑıÑĤи
    -0.16
    ken
    -0.15
    rame
    -0.15
    addir
    -0.14
    anter
    -0.14
    547
    -0.14
    mpar
    -0.14
    stras
    -0.14
    ç¤
    -0.14
    POSITIVE LOGITS
     necessarily
    0.17
    withstanding
    0.16
    ANJI
    0.15
    tingham
    0.15
     ph
    0.15
    oday
    0.15
    928
    0.15
    imson
    0.14
    reek
    0.14
    nes
    0.14
    Act Density 0.040%

    No Known Activations