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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures involving modal verbs and their applications in hypothetical or conditional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pokrač
    -0.66
     geweest
    -0.59
     cae
    -0.56
     tombé
    -0.55
    UserScript
    -0.55
     tombe
    -0.53
    worden
    -0.53
     assisti
    -0.53
     niitä
    -0.53
     cayó
    -0.52
    POSITIVE LOGITS
    afficheront
    0.71
    devamını
    0.65
    +#+#
    0.64
    setViewportView
    0.63
    참고
    0.56
    BASELINE
    0.52
    RUnlock
    0.52
    englanniksi
    0.50
    Portail
    0.50
     indeed
    0.49
    Act Density 0.049%

    No Known Activations