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

    Neuronpedia

    INDEX
    Explanations

    questions and uncertainty in statements

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

    depending on question words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Yet
    -0.29
     Yet
    -0.28
     yet
    -0.27
     poor
    -0.25
     평
    -0.23
     to
    -0.23
     due
    -0.22
    uramente
    -0.22
    ɜ
    -0.22
    0
    -0.22
    POSITIVE LOGITS
     betweenstory
    0.88
    DockStyle
    0.87
     виправивши
    0.85
    IsMutable
    0.81
     Monfieur
    0.79
     invokingState
    0.79
    iſchen
    0.78
    niſſe
    0.77
    <pad>
    0.77
    enumii
    0.77
    Act Density 0.020%

    No Known Activations