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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating presentation or reporting of data and results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.69
     AssemblyCompany
    -0.61
    UnsafeEnabled
    -0.57
    homonymie
    -0.55
    adaptiveStyles
    -0.53
     Normdatei
    -0.52
     CreateTagHelper
    -0.51
     smtplib
    -0.50
    untungan
    -0.49
     ríos
    -0.49
    POSITIVE LOGITS
    entennial
    0.63
    показания
    0.61
     Māori
    0.60
    ettes
    0.58
    EditorGUILayout
    0.55
     TextAlign
    0.54
     DPM
    0.53
    ulateur
    0.53
     displays
    0.52
     Pn
    0.52
    Act Density 0.022%

    No Known Activations