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

    Neuronpedia

    INDEX
    Explanations

    expressions of societal observations and moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unicorn
    -0.15
     Simpsons
    -0.14
    PIO
    -0.14
    abei
    -0.14
    ernes
    -0.14
    åijĺ
    -0.14
     extra
    -0.13
    reetings
    -0.13
     astronaut
    -0.13
    æĪ¶
    -0.13
    POSITIVE LOGITS
     circumstance
    0.24
     Nature
    0.22
     gravity
    0.21
     nature
    0.21
     fate
    0.19
     History
    0.19
    Nature
    0.19
     Those
    0.19
    gravity
    0.19
     history
    0.19
    Act Density 0.127%

    No Known Activations