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

    Neuronpedia

    INDEX
    Explanations

    terms related to "heavy" and associated weightiness or seriousness, particularly in contexts involving heavy-duty items or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /wiki
    -0.15
    enberg
    -0.14
     uncert
    -0.14
    WindowSize
    -0.14
    ège
    -0.14
    iband
    -0.14
    -FIRST
    -0.14
    osen
    -0.14
    UDA
    -0.14
    oji
    -0.14
    POSITIVE LOGITS
    -duty
    0.31
    weights
    0.24
    -weight
    0.20
     hitters
    0.20
     duty
    0.19
    ening
    0.19
    weight
    0.19
     Duty
    0.18
    ened
    0.17
    -handed
    0.17
    Act Density 0.017%

    No Known Activations