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

    Neuronpedia

    INDEX
    Explanations

    references to superhero characters and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters and their attributes in superhero narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.81
    cript
    -0.76
    hip
    -0.75
    say
    -0.73
    pai
    -0.73
    peat
    -0.72
    acles
    -0.69
    etics
    -0.68
    itism
    -0.66
    opathy
    -0.66
    POSITIVE LOGITS
     Ducks
    0.76
    aneers
    0.74
     Hulk
    0.72
    lda
    0.71
     Avenger
    0.69
     Drac
    0.68
     Breaker
    0.68
    oster
    0.68
    ernaut
    0.66
    inous
    0.66
    Act Density 0.092%

    No Known Activations