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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contribution or causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     introd
    -0.58
     remarqu
    -0.56
    []>(
    -0.54
     >=",
    -0.54
     approached
    -0.54
    rolle
    -0.54
    cinated
    -0.54
    氓
    -0.53
    irin
    -0.53
    DEA
    -0.52
    POSITIVE LOGITS
     Contributing
    0.74
     contributing
    0.74
     contributes
    0.73
     contribution
    0.72
     Contribute
    0.71
     contribute
    0.71
     contributors
    0.71
     fueling
    0.70
     contributor
    0.70
     contribué
    0.67
    Act Density 0.279%

    No Known Activations