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

    Neuronpedia

    INDEX
    Explanations

    indications of delusions and beliefs related to mental disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugin
    -0.16
    ogui
    -0.15
    elon
    -0.15
    laus
    -0.15
    zcze
    -0.15
    trys
    -0.15
    illon
    -0.15
    ugen
    -0.14
    apphire
    -0.14
     niên
    -0.14
    POSITIVE LOGITS
     entitlement
    0.19
     superior
    0.18
     unique
    0.18
    kowski
    0.16
     inf
    0.15
     entitled
    0.15
     victim
    0.15
    unique
    0.15
     Unique
    0.15
     convinced
    0.14
    Act Density 0.183%

    No Known Activations