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

    Neuronpedia

    INDEX
    Explanations

    instances of negation or exclamation markers, particularly the "!" symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -0.66
    Erreferentziak
    -0.64
    jasama
    -0.64
     zijne
    -0.63
    ⓧ
    -0.62
    ніципалі
    -0.61
    ConstraintMaker
    -0.61
     InputDecoration
    -0.60
    haviours
    -0.60
     indígen
    -0.59
    POSITIVE LOGITS
    !
    2.28
     !
    1.73
    !!
    1.67
    !(
    1.67
    !:
    1.57
    !!!
    1.52
    !\
    1.49
    !-
    1.49
    !<
    1.48
    !</
    1.48
    Act Density 0.141%

    No Known Activations