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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to obligation and actions that indicate compliance or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.77
    icism
    -0.57
    UnusedPrivate
    -0.56
    RTLU
    -0.54
     contextLoads
    -0.54
     Blond
    -0.53
    %)$
    -0.52
     Petra
    -0.52
     nakalista
    -0.51
     fotografico
    -0.51
    POSITIVE LOGITS
     mussten
    0.83
     musste
    0.74
     ComVisible
    0.67
     necessariamente
    0.65
     пришлось
    0.64
    StructEnd
    0.63
    CppMethod
    0.63
     terpaksa
    0.62
    must
    0.62
     necesariamente
    0.60
    Act Density 0.291%

    No Known Activations