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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases indicating skepticism or questioning of narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apl
    -0.16
    leh
    -0.15
    ije
    -0.14
    inski
    -0.14
    تÙģ
    -0.14
    uby
    -0.14
    ãĥĥ
    -0.13
     (&
    -0.13
    isp
    -0.13
    comed
    -0.13
    POSITIVE LOGITS
    ìŀIJ
    0.16
    -widgets
    0.14
     strains
    0.14
    catid
    0.14
     verg
    0.13
     validationResult
    0.13
    ackages
    0.13
    loy
    0.13
     conse
    0.13
     spoilers
    0.13
    Act Density 0.000%

    No Known Activations