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

    Neuronpedia

    INDEX
    Explanations

    Latin letters C with a cedilla below

    oai_token-act-pair · gpt-3.5-turbo

    instances of questioning or requesting action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ``
    -1.17
    `.
    -1.03
     ``
    -1.02
    `,
    -0.96
    Âł
    -0.96
    `
    -0.86
     Âł
    -0.77
    ````
    -0.76
    ÃŃs
    -0.73
    ?".
    -0.73
    POSITIVE LOGITS
     —
    2.18
     ÂŃ
    1.35
     âĢķ
    1.25
    ÂŃ
    1.00
     pic
    0.99
     »
    0.91
    ——
    0.88
     âĢ¦
    0.85
     (@
    0.85
    .—
    0.85
    Act Density 0.232%

    No Known Activations