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

    Neuronpedia

    INDEX
    Explanations

    themes of personal responsibility and self-empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uml
    -0.15
    WEEN
    -0.15
    vious
    -0.14
     Intr
    -0.14
    ewise
    -0.14
    uji
    -0.14
    .soft
    -0.14
    primer
    -0.14
     Ing
    -0.14
     Tol
    -0.14
    POSITIVE LOGITS
    /self
    0.25
     self
    0.20
    (Self
    0.19
    self
    0.18
    -self
    0.18
    Self
    0.18
    ocab
    0.18
     Self
    0.16
     independently
    0.16
     SELF
    0.16
    Act Density 0.138%

    No Known Activations