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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific shapes and structuring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ReactDOM
    -0.71
    AnchorStyles
    -0.69
    Ephe
    -0.61
     actionMode
    -0.60
     кӀош
    -0.57
    succ
    -0.57
    nanoTime
    -0.57
    rophes
    -0.56
    <?
    -0.56
    SpringRunner
    -0.55
    POSITIVE LOGITS
     structured
    0.81
    structured
    0.74
     colored
    0.72
     Shaped
    0.72
    Shaped
    0.71
     rotating
    0.70
     shaped
    0.69
     autorytatywna
    0.69
     coloured
    0.69
    mstyle
    0.69
    Act Density 0.091%

    No Known Activations