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

    Neuronpedia

    INDEX
    Explanations

    references to things that are considered classic

    oai_token-act-pair · gpt-3.5-turbo

    references to classic items or works across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earcher
    -0.70
    OTUS
    -0.68
    reon
    -0.67
    lesh
    -0.67
    rollment
    -0.64
    lying
    -0.63
    robe
    -0.62
    hop
    -0.60
    larg
    -0.60
    pta
    -0.60
    POSITIVE LOGITS
    arily
    0.90
    ised
    0.83
     Revival
    0.81
    ists
    0.79
    isable
    0.76
    ized
    0.75
    isation
    0.74
    ist
    0.74
     arcade
    0.74
     ante
    0.73
    Act Density 0.038%

    No Known Activations