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

    Neuronpedia

    INDEX
    Explanations

    things that are considered invalid or need to be invalidated

    oai_token-act-pair · gpt-3.5-turbo

    terms related to validity and invalidation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bio
    -0.78
    ILA
    -0.77
    illance
    -0.73
    Hat
    -0.71
    asio
    -0.70
    UTERS
    -0.69
    knit
    -0.68
    RH
    -0.68
    ynthesis
    -0.68
    bors
    -0.66
    POSITIVE LOGITS
     invalid
    1.11
    ating
    0.84
     unfocusedRange
    0.84
    ated
    0.78
     Invalid
    0.78
    Invalid
    0.72
     overwrite
    0.71
    ates
    0.68
    valid
    0.66
    ãĤ¹ãĥĪ
    0.66
    Act Density 0.006%

    No Known Activations