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

    Neuronpedia

    INDEX
    Explanations

    terms related to punishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.58
    BagConstraints
    -0.52
    +:+
    -0.51
    heide
    -0.49
    exitRule
    -0.49
     betweenstory
    -0.47
    closedir
    -0.43
    󠁬
    -0.42
    ритори
    -0.42
    ideration
    -0.41
    POSITIVE LOGITS
    react
    0.66
     react
    0.62
     pun
    0.61
     חיצוניים
    0.60
     React
    0.59
     AssemblyTitle
    0.59
    React
    0.58
     MonoBehaviour
    0.57
     reacts
    0.56
    pun
    0.56
    Act Density 0.348%

    No Known Activations