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

    Neuronpedia

    INDEX
    Explanations

    words indicating ongoing or repeated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oad
    -0.16
    erton
    -0.16
    lier
    -0.16
    liers
    -0.15
     赤
    -0.14
    acco
    -0.14
    ürlich
    -0.13
     talented
    -0.13
    asl
    -0.13
    akhir
    -0.13
    POSITIVE LOGITS
     around
    0.24
     providing
    0.19
    around
    0.19
     Around
    0.19
    Around
    0.19
     voted
    0.18
     called
    0.17
     described
    0.17
     fixtures
    0.16
     active
    0.16
    Act Density 0.043%

    No Known Activations