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

    Neuronpedia

    INDEX
    Explanations

    words related to retractions or corrections in written content

    oai_token-act-pair · gpt-3.5-turbo

    references to corrections or reactions in reports or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.78
    tips
    -0.73
    STEM
    -0.70
    ï¸
    -0.67
    STD
    -0.66
    WAYS
    -0.66
    )=(
    -0.65
    Shell
    -0.64
    latest
    -0.64
    ãĥĨãĤ£
    -0.63
    POSITIVE LOGITS
    ainer
    1.19
    ribut
    1.18
    raction
    1.14
    reating
    1.08
    rans
    1.06
    ention
    1.04
    itled
    1.01
    rieve
    1.01
    raining
    1.00
    reat
    0.99
    Act Density 0.014%

    No Known Activations