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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming and syntax

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant changes or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]."
    -0.67
    )."
    -0.63
    .).
    -0.63
    ).[
    -0.57
    )).
    -0.56
    }.
    -0.56
    '."
    -0.54
    ).
    -0.53
    .'"
    -0.53
    .""
    -0.51
    POSITIVE LOGITS
    ':
    0.57
    \":
    0.49
     understatement
    0.47
     ·
    0.44
    earchers
    0.43
    epad
    0.43
    TPPStreamerBot
    0.41
    arij
    0.41
    20439
    0.40
    resa
    0.40
    Act Density 4.040%

    No Known Activations