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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional experiences and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oulos
    -0.19
    chwitz
    -0.15
    ixel
    -0.15
    åŃĿ
    -0.15
    ardi
    -0.14
     Hint
    -0.14
    istro
    -0.14
     Gazette
    -0.14
    RTOS
    -0.14
    deniz
    -0.14
    POSITIVE LOGITS
     odd
    0.28
     weir
    0.24
     weird
    0.23
     peculiar
    0.22
     strange
    0.21
    isol
    0.20
     isolation
    0.19
    odd
    0.19
     strang
    0.19
    _odd
    0.19
    Act Density 0.016%

    No Known Activations