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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressions of opinion or belief

    oai_token-act-pair · gpt-3.5-turbo

    terms related to notable individuals and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAT
    -0.58
    PDATE
    -0.55
     Dism
    -0.45
     Removal
    -0.45
     Reporter
    -0.44
     Cosponsors
    -0.44
     Accountability
    -0.42
     Hearing
    -0.42
     LV
    -0.42
     Palest
    -0.42
    POSITIVE LOGITS
    rylic
    0.58
    ensable
    0.56
    vation
    0.56
    iatus
    0.55
    iazep
    0.54
    ecided
    0.51
    smanship
    0.50
    imester
    0.50
    iversary
    0.49
    iosity
    0.49
    Act Density 7.676%

    No Known Activations