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

    Neuronpedia

    INDEX
    Explanations

    increasing or growing trends or numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to increasing quantities or counts related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.74
     quir
    -0.67
    cients
    -0.63
    Brave
    -0.61
     1964
    -0.60
     Gleaming
    -0.59
     Mat
    -0.59
     unbiased
    -0.58
    verning
    -0.58
     vetoed
    -0.58
    POSITIVE LOGITS
    osph
    0.79
    catentry
    0.76
    ende
    0.70
    pees
    0.68
    soon
    0.67
    pread
    0.64
    illon
    0.64
    yout
    0.63
    izons
    0.62
    ãĥĢ
    0.62
    Act Density 0.200%

    No Known Activations