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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical attributes or characteristics in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to size, characteristics, and state of objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !.
    -0.77
    $.
    -0.76
    `.
    -0.75
    *.
    -0.68
    ().
    -0.66
    Ú
    -0.65
    ilaterally
    -0.64
     etc
    -0.63
    utics
    -0.62
    chwitz
    -0.62
    POSITIVE LOGITS
     trio
    0.67
     administrator
    0.59
     irony
    0.59
    named
    0.58
     lieutenant
    0.58
    haired
    0.57
     duo
    0.57
     question
    0.56
     gunman
    0.56
     omission
    0.56
    Act Density 0.791%

    No Known Activations