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

    Neuronpedia

    INDEX
    Explanations

    prepositions and adverbs related to causation and manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.75
     autorytatywna
    -0.74
    Autoritní
    -0.71
     externi
    -0.67
    jsii
    -0.67
    Diwedd
    -0.64
    Collegamenti
    -0.63
    addCriterion
    -0.63
     TextAppearance
    -0.62
    Дереккөздер
    -0.62
    POSITIVE LOGITS
     which
    0.81
     waarop
    0.60
     οποίο
    0.55
    which
    0.55
    :");
    0.53
    ärsk
    0.52
    ">';
    0.52
    ">'.$
    0.52
    '>";
    0.50
     kyse
    0.50
    Act Density 0.424%

    No Known Activations