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

    Neuronpedia

    INDEX
    Explanations

    words related to societal or cultural contexts, especially regarding issues or challenges

    oai_token-act-pair · gpt-3.5-turbo

    contexts indicating specific conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apult
    -0.78
     Deer
    -0.63
     Mant
    -0.62
    vous
    -0.60
    leaf
    -0.57
    Chel
    -0.57
    cade
    -0.57
    Laun
    -0.57
    swick
    -0.57
    hook
    -0.55
    POSITIVE LOGITS
    upon
    1.14
    abouts
    0.97
    soever
    0.88
     nobody
    0.71
    ornia
    0.69
     neither
    0.68
     electors
    0.68
     people
    0.66
     everything
    0.65
    ertodd
    0.65
    Act Density 0.087%

    No Known Activations