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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of statistical data or percentages in a structured and formal context

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations or statistics related to demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Phant
    -0.76
     curse
    -0.71
     pestic
    -0.69
    ioxide
    -0.69
     breathe
    -0.66
     flare
    -0.66
    illard
    -0.66
    anus
    -0.66
     feather
    -0.66
    orp
    -0.65
    POSITIVE LOGITS
    .�
    0.76
     Mellon
    0.68
    eral
    0.64
    erest
    0.64
    utsche
    0.63
    �
    0.63
    POL
    0.61
    eret
    0.61
    .''.
    0.61
    ----------------------------------------------------------------
    0.61
    Act Density 0.000%

    No Known Activations