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

    Neuronpedia

    INDEX
    Explanations

    terms related to various geographical locations and events

    oai_token-act-pair · gpt-3.5-turbo

    a specific symbol or character, which appears frequently and might indicate formatting or important markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ``
    -1.20
    Âł
    -0.93
    ````
    -0.87
    `,
    -0.85
     ``
    -0.83
    ³³³
    -0.81
    `.
    -0.81
    `
    -0.78
    ³³
    -0.75
     `
    -0.75
    POSITIVE LOGITS
     —
    3.19
     âĢķ
    2.19
     ÂŃ
    1.82
    —
    1.78
     --
    1.51
    —"
    1.49
     âĢ¦
    1.47
     –
    1.38
    .—
    1.37
    Enlarge
    1.29
    Act Density 0.088%

    No Known Activations