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

    Neuronpedia

    INDEX
    Explanations

    questions expressing confusion or disbelief about social expectations and criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypi
    -0.18
    imbus
    -0.16
     adipiscing
    -0.15
    culus
    -0.14
    .pg
    -0.14
    odash
    -0.13
    ando
    -0.13
    atcher
    -0.13
    reh
    -0.13
    Net
    -0.13
    POSITIVE LOGITS
    ancel
    0.17
    ault
    0.15
    unan
    0.15
    .ibatis
    0.15
     Burton
    0.15
    omers
    0.14
     democr
    0.14
     funnel
    0.14
     burden
    0.14
    VML
    0.14
    Act Density 0.149%

    No Known Activations