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

    Neuronpedia

    INDEX
    Explanations

    concepts related to responsibility and understanding in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.66
    enterOuterAlt
    -0.61
     يتيمه
    -0.59
    يكب
    -0.55
     endblock
    -0.54
    RTLU
    -0.54
    ništvo
    -0.53
    WebVitals
    -0.52
    DockStyle
    -0.52
    XmlRootElement
    -0.51
    POSITIVE LOGITS
     things
    1.06
     others
    0.91
     situations
    0.85
     dingen
    0.78
     OTHERS
    0.77
     Others
    0.75
     mistakes
    0.74
    others
    0.73
    事物
    0.73
     THINGS
    0.71
    Act Density 0.798%

    No Known Activations