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

    Neuronpedia

    INDEX
    Explanations

    inconsistencies and contradictions in narratives or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doma
    -0.16
    ceptive
    -0.15
    _:*
    -0.14
    parer
    -0.13
    umbo
    -0.13
    isini
    -0.13
     reminded
    -0.13
    ä»Ĭå¹´
    -0.13
    herits
    -0.13
    ê´
    -0.13
    POSITIVE LOGITS
     story
    0.22
     version
    0.21
     timeline
    0.19
     claims
    0.19
     versions
    0.19
    claims
    0.19
     claimed
    0.18
     Claims
    0.18
     accounts
    0.18
    accounts
    0.18
    Act Density 0.224%

    No Known Activations