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

    Neuronpedia

    INDEX
    Explanations

    words related to accusations or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "s"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.79
     Wikileaks
    -0.72
     unrestricted
    -0.68
     incumbent
    -0.64
     WikiLeaks
    -0.62
     Sacrament
    -0.61
     bases
    -0.60
     Scourge
    -0.60
     Pharaoh
    -0.60
     undecided
    -0.59
    POSITIVE LOGITS
    uss
    1.14
    outher
    1.14
    igm
    1.13
    arah
    1.13
    agging
    1.13
    idd
    1.13
    arin
    1.11
    iren
    1.10
    igma
    1.10
    ams
    1.09
    Act Density 0.023%

    No Known Activations