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

    Neuronpedia

    INDEX
    Explanations

    alternative text for images and scheduling information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     synthetic
    -0.51
     material
    -0.49
     physical
    -0.44
     thought
    -0.44
     reference
    -0.43
     combination
    -0.43
     symbol
    -0.43
     typical
    -0.43
     character
    -0.42
     complex
    -0.42
    POSITIVE LOGITS
    \{\\
    0.63
     MainAxisSize
    0.61
     виправивши
    0.59
     PagesJaunes
    0.59
     الرياضيه
    0.57
    rrggbb
    0.56
     ProtoMessage
    0.56
     nôtre
    0.56
     ujednoznacz
    0.56
    windowFixed
    0.56
    Act Density 0.207%

    No Known Activations