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

    Neuronpedia

    INDEX
    Explanations

    phrases related to complaints or negativity

    oai_token-act-pair · gpt-3.5-turbo

    references to deplorable situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬âĸ¬
    -0.83
    âĸ¬
    -0.80
    HAHA
    -0.73
    eers
    -0.71
    QUI
    -0.70
    hold
    -0.66
    ////////////////////////////////
    -0.65
    ModLoader
    -0.65
     Logged
    -0.65
    eer
    -0.63
    POSITIVE LOGITS
    acement
    1.33
    enty
    1.21
    asma
    1.20
    umbing
    1.17
    acements
    1.10
    atoon
    1.09
    atinum
    1.09
    osion
    1.08
    anted
    1.04
    ains
    1.00
    Act Density 0.013%

    No Known Activations