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

    Neuronpedia

    INDEX
    Explanations

    overemphasized or belittled information

    oai_token-act-pair · gpt-3.5-turbo

    words related to triviality and insignificance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.70
    artney
    -0.70
    elson
    -0.70
    angelo
    -0.69
    oother
    -0.66
    anwhile
    -0.65
    yer
    -0.63
    olan
    -0.63
    andr
    -0.61
    ravings
    -0.60
    POSITIVE LOGITS
    ities
    1.03
    ity
    0.96
    istically
    0.92
    ifiable
    0.88
    itized
    0.87
     trivial
    0.86
     inconven
    0.84
     innocuous
    0.83
    izes
    0.83
    ization
    0.83
    Act Density 0.011%

    No Known Activations