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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "TODO" indicating tasks or actions that need to be completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Murat
    -0.69
    SourceChecksum
    -0.64
     Pizarro
    -0.60
    UnsafeEnabled
    -0.60
    佣
    -0.58
     Wiz
    -0.57
     lungs
    -0.57
     Visconti
    -0.54
     foot
    -0.53
    foot
    -0.53
    POSITIVE LOGITS
     dare
    0.95
     TODO
    0.92
    帖最后由
    0.77
     dares
    0.76
    DAOImpl
    0.72
    PhysRevD
    0.72
     emphasised
    0.71
     emphasise
    0.70
    makeConstraints
    0.70
     CURIAM
    0.70
    Act Density 0.044%

    No Known Activations