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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific events or entities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic expressions and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     juggling
    -0.78
     coax
    -0.73
     occasional
    -0.72
     slower
    -0.69
     secretaries
    -0.65
     broker
    -0.65
     loft
    -0.65
    hiba
    -0.64
     cob
    -0.63
     shrink
    -0.63
    POSITIVE LOGITS
    âĢ
    2.03
    »
    1.78
    ãĢ
    1.66
    [/
    1.62
    ãĢį
    1.60
    </
    1.57
     âĢ
    1.57
    ãĢı
    1.42
    \",
    1.41
    âĦ¢
    1.36
    Act Density 0.355%

    No Known Activations