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

    Neuronpedia

    INDEX
    Explanations

    instances of modal verbs and their various usages in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.67
    ImageContext
    -0.58
     desmotivaciones
    -0.57
    oarece
    -0.55
    jenigen
    -0.54
    ものです
    -0.54
    __':
    -0.54
    новништво
    -0.54
     utafitiHapana
    -0.53
    "}")
    -0.52
    POSITIVE LOGITS
    HAVE
    0.31
     werden
    0.31
     und
    0.31
    assertRaises
    0.31
    KEEP
    0.29
     [*]
    0.29
    detach
    0.28
     uns
    0.28
    have
    0.28
    tund
    0.28
    Act Density 0.055%

    No Known Activations