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

    Neuronpedia

    INDEX
    Explanations

    concepts related to self-reflection and individuality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ujud
    -0.41
    antel
    -0.40
    acá
    -0.39
     sahiptir
    -0.38
    ▼
    -0.38
    ssen
    -0.38
    uge
    -0.38
    temu
    -0.37
    runApp
    -0.37
    TAC
    -0.37
    POSITIVE LOGITS
     Self
    1.20
     self
    1.19
    Self
    1.18
     SELF
    1.17
    self
    1.09
    SELF
    1.08
     Myself
    1.05
     personal
    1.03
     myſelf
    1.02
    myself
    1.02
    Act Density 0.459%

    No Known Activations