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

    Neuronpedia

    INDEX
    Explanations

    complex relationships and contradictions in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of negation or contradiction (words/phrases expressing "not", "no", disagreement or refusal).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    󠁢
    -0.46
    랬
    -0.42
    surprised
    -0.41
     invitación
    -0.38
     NSCoder
    -0.36
     invitados
    -0.36
     intptr
    -0.36
    contentLoaded
    -0.36
     casais
    -0.36
     invitaciones
    -0.35
    POSITIVE LOGITS
    $_['
    0.57
    0.52
    (__('
    0.49
     invokingState
    0.48
    EDEFAULT
    0.47
    /*
    0.46
     AssemblyTitle
    0.45
     &___
    0.44
    0.43
     Waray
    0.43
    Act Density 0.101%

    No Known Activations