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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future intentions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ward
    -0.18
    zug
    -0.17
    747
    -0.17
    223
    -0.16
    y
    -0.16
    ro
    -0.15
    rait
    -0.15
    .tc
    -0.15
     Herr
    -0.15
    145
    -0.14
    POSITIVE LOGITS
    ONES
    0.16
    ê²½
    0.16
    WP
    0.15
    onne
    0.15
     expected
    0.15
    ying
    0.14
    tes
    0.14
    expected
    0.14
    etimes
    0.14
    illard
    0.14
    Act Density 0.050%

    No Known Activations