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

    Neuronpedia

    INDEX
    Explanations

    terms related to testing and inspection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.66
    keteers
    -0.46
    netinet
    -0.46
     GRANDE
    -0.45
    ggio
    -0.43
    ydı
    -0.42
     Zeitpunkt
    -0.41
    ENSUS
    -0.41
    tai
    -0.41
     MO
    -0.41
    POSITIVE LOGITS
     hindurch
    1.00
    writeField
    0.90
     through
    0.81
    ="@+
    0.81
    through
    0.81
    THROUGH
    0.80
     heen
    0.71
     attraverso
    0.71
    DebuggerNonUser
    0.70
     hinweg
    0.69
    Act Density 0.336%

    No Known Activations