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

    Neuronpedia

    INDEX
    Explanations

    references to specific popular entertainment titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of notable anime titles and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERTISEMENT
    -0.77
    ĺħ
    -0.76
    İĭ
    -0.76
    Dialogue
    -0.70
    ļéĨĴ
    -0.70
    ulty
    -0.70
    idents
    -0.70
    IAS
    -0.68
    anwhile
    -0.68
    ourses
    -0.67
    POSITIVE LOGITS
     acronym
    1.00
     abbre
    0.86
     underrated
    0.83
     standalone
    0.81
     derivative
    0.81
     name
    0.77
     incarn
    0.74
     minimalist
    0.73
     synonymous
    0.72
     slang
    0.72
    Act Density 0.420%

    No Known Activations