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

    Neuronpedia

    INDEX
    Explanations

    references to political events and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umba
    -0.19
    rowsable
    -0.16
    iazza
    -0.15
    enson
    -0.15
    enz
    -0.15
    Ñī
    -0.15
    795
    -0.14
     Jacket
    -0.14
    ocator
    -0.14
    inherits
    -0.14
    POSITIVE LOGITS
     credibility
    0.18
    incer
    0.18
    Leaks
    0.17
     witness
    0.15
    irut
    0.15
     witnesses
    0.15
     credible
    0.14
    dam
    0.14
     lies
    0.14
    ertime
    0.14
    Act Density 0.228%

    No Known Activations