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

    Neuronpedia

    INDEX
    Explanations

    instances of denial or rejection of claims or accusations

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

    denied involvement or accusations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     turistas
    -0.46
    ždy
    -0.43
     temáticas
    -0.41
    ϖ
    -0.41
     culturas
    -0.41
     culturelle
    -0.41
     sociedades
    -0.40
     tiroirs
    -0.40
     quema
    -0.39
     edades
    -0.39
    POSITIVE LOGITS
     denied
    0.74
    denied
    0.58
     Denied
    0.57
     denies
    0.53
     Biôgrafia
    0.51
     bVar
    0.51
     Anſ
    0.49
     refuted
    0.49
     Answered
    0.47
     rejected
    0.47
    Act Density 0.045%

    No Known Activations