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

    Neuronpedia

    INDEX
    Explanations

    references to societal cultural themes and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ity
    -0.22
    asil
    -0.18
    ikers
    -0.17
    idas
    -0.17
    rega
    -0.16
    ifier
    -0.16
    laus
    -0.16
    itude
    -0.15
    OrCreate
    -0.15
    ITY
    -0.15
    POSITIVE LOGITS
     shock
    0.26
    lle
    0.23
    Shock
    0.22
     Shock
    0.22
    urally
    0.20
    anzi
    0.19
    tainment
    0.18
     shocks
    0.17
    tte
    0.17
    urum
    0.17
    Act Density 0.026%

    No Known Activations