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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating economic or social challenges and illusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axe
    -0.18
    ìĦĿ
    -0.16
    ewise
    -0.15
    456
    -0.15
    ummy
    -0.15
    865
    -0.14
    enburg
    -0.14
    azing
    -0.14
     HoÃłng
    -0.14
    etz
    -0.14
    POSITIVE LOGITS
    ptions
    0.17
     lip
    0.16
    ptic
    0.15
    .ws
    0.14
    HECK
    0.14
    -divider
    0.14
     Implement
    0.14
    abor
    0.14
    oti
    0.14
     IO
    0.14
    Act Density 0.330%

    No Known Activations