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

    Neuronpedia

    INDEX
    Explanations

    themes related to body image and self-acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HRESULT
    -0.13
    Ãłnh
    -0.13
    .pb
    -0.13
    óm
    -0.13
    SPARENT
    -0.13
    urret
    -0.13
     obstruction
    -0.13
    Ïģε
    -0.13
    swift
    -0.13
    मन
    -0.13
    POSITIVE LOGITS
     confidence
    0.50
     Confidence
    0.49
     self
    0.45
    -confidence
    0.42
    confidence
    0.41
     confident
    0.37
     Self
    0.37
    -self
    0.34
    (self
    0.32
    Self
    0.32
    Act Density 0.222%

    No Known Activations