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

    Neuronpedia

    INDEX
    Explanations

    character names from a fictional story

    oai_token-act-pair · gpt-3.5-turbo

    names of characters and emotional interactions between them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Indiana
    -0.78
    draw
    -0.73
    FINE
    -0.73
    Ú
    -0.73
    VICE
    -0.71
    eteria
    -0.70
    HAEL
    -0.69
    IRT
    -0.68
    irs
    -0.68
    dos
    -0.67
    POSITIVE LOGITS
     Pyrrha
    0.85
     Nik
    0.80
     Ruby
    0.77
     Dot
    0.77
     Swift
    0.76
     Uz
    0.75
     Weiss
    0.73
     Yang
    0.72
     Arc
    0.71
     Nora
    0.70
    Act Density 0.028%

    No Known Activations