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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities or comparisons that suggest a lower measure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agedList
    -0.15
    oug
    -0.15
    YD
    -0.15
    erken
    -0.15
    tas
    -0.14
    )test
    -0.14
    trl
    -0.14
    munition
    -0.14
    apesh
    -0.14
    Lists
    -0.14
    POSITIVE LOGITS
    ened
    0.47
    ening
    0.46
     than
    0.41
    -than
    0.40
    Than
    0.31
    ens
    0.30
    _than
    0.29
     THAN
    0.29
     Than
    0.28
    ons
    0.28
    Act Density 0.034%

    No Known Activations