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

    Neuronpedia

    INDEX
    Explanations

    instances that acknowledge or note reasons for behaviors or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    بوابة
    -0.67
     loop
    -0.59
     Loop
    -0.58
     loops
    -0.58
     supporto
    -0.58
    extAlignment
    -0.58
    TemporalType
    -0.57
     Архів
    -0.56
    UIControlState
    -0.56
     Diſ
    -0.55
    POSITIVE LOGITS
    ArgsConstructor
    0.72
    ftagPool
    0.71
     InputDecoration
    0.64
     betweenstory
    0.63
    yntaxException
    0.63
     crossorigin
    0.63
     reason
    0.62
    openzeppelin
    0.61
    RegressionTest
    0.59
    ListItemIcon
    0.56
    Act Density 0.196%

    No Known Activations