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

    Neuronpedia

    INDEX
    Explanations

    references to ego and vanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letics
    -0.17
    ArrayOf
    -0.17
    Extern
    -0.15
    Descriptors
    -0.15
    айд
    -0.14
    мена
    -0.14
    åĬ
    -0.14
     ΣÏĩ
    -0.14
    iant
    -0.14
    IEWS
    -0.14
    POSITIVE LOGITS
     ego
    0.22
    ego
    0.18
     eg
    0.17
    lector
    0.16
     narciss
    0.15
     Folk
    0.15
    uber
    0.15
     Narc
    0.14
     intoxic
    0.14
     Satisfaction
    0.14
    Act Density 0.234%

    No Known Activations