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

    Neuronpedia

    INDEX
    Explanations

    strong negations or refusals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bourgoin
    -0.89
     PyTuple
    -0.69
     Amalia
    -0.66
     gangen
    -0.66
     cref
    -0.65
    หวัด
    -0.64
     condamné
    -0.62
     Constitucional
    -0.61
     contribué
    -0.60
     devons
    -0.59
    POSITIVE LOGITS
     no
    1.28
     No
    1.09
     nessun
    1.02
     nessuna
    1.02
     NO
    0.96
    No
    0.96
     any
    0.91
    Kein
    0.91
     ningún
    0.88
     ника
    0.86
    Act Density 0.089%

    No Known Activations