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

    Neuronpedia

    INDEX
    Explanations

    commands or obligations related to actions that must be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.84
    Berikut
    -0.73
    dema
    -0.65
     Walling
    -0.65
     Crowe
    -0.64
     infar
    -0.63
    ViewFeatures
    -0.62
     BorderSide
    -0.62
    bage
    -0.62
     själ
    -0.61
    POSITIVE LOGITS
     must
    1.55
     MUST
    1.49
     Must
    1.46
    Must
    1.42
    must
    1.35
    MUST
    1.31
     mustn
    1.11
    Gotta
    1.00
     doit
    1.00
     måste
    0.99
    Act Density 0.048%

    No Known Activations