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

    Neuronpedia

    INDEX
    Explanations

    references to particular pieces of art or media likely in a digital space

    oai_token-act-pair · gpt-3.5-turbo

    special characters and formatting symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accrued
    -0.98
     amounts
    -0.90
     mandate
    -0.89
     confir
    -0.89
     broadly
    -0.88
     responding
    -0.88
     range
    -0.88
     affected
    -0.88
     outcomes
    -0.87
     describ
    -0.87
    POSITIVE LOGITS
    Lady
    1.47
    Thunder
    1.47
    Flying
    1.46
    Moon
    1.45
    Haunted
    1.45
    Ghost
    1.44
    Sweet
    1.44
    Monster
    1.44
    Winged
    1.42
    Golden
    1.42
    Act Density 0.316%

    No Known Activations