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

    Neuronpedia

    INDEX
    Explanations

    sentences describing a difficult experience

    oai_token-act-pair · gemini-2.0-flash

    terms related to stress

    np_token-act-pair-logits · gpt-4o-mini

    stress

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.54
    MENAFN
    -0.53
     possible
    -0.52
    ódnica
    -0.52
    EFIAPI
    -0.52
    possible
    -0.51
     الرياضيه
    -0.50
    賓
    -0.50
    CppCodeGen
    -0.49
    Allowed
    -0.49
    POSITIVE LOGITS
     stressful
    0.61
    featureID
    0.56
     STRESS
    0.55
     onOptions
    0.51
     setCode
    0.50
    DockStyle
    0.49
    argout
    0.49
    iastes
    0.47
     menyeb
    0.47
     Stress
    0.47
    Act Density 1.277%

    No Known Activations