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

    Neuronpedia

    INDEX
    Explanations

    phrases related to controversial statements and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onViewCreated
    -0.79
    phosa
    -0.72
     avoient
    -0.69
     houſe
    -0.68
     étoient
    -0.66
     coö
    -0.65
     bahay
    -0.64
    ergies
    -0.64
     itſelf
    -0.61
     myſelf
    -0.61
    POSITIVE LOGITS
     allegedly
    0.61
    ագրություններ
    0.58
     controversy
    0.57
    idon
    0.53
    бар
    0.52
     controversial
    0.50
     proposed
    0.49
    myModal
    0.48
    SequentialGroup
    0.48
     कथ
    0.48
    Act Density 0.678%

    No Known Activations