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

    Neuronpedia

    INDEX
    Explanations

    phrases that signify disengagement or avoidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Życiorys
    -0.86
     IMA
    -0.86
     Wren
    -0.79
    Parcelize
    -0.79
     nahilalakip
    -0.79
    quelize
    -0.76
    esgue
    -0.76
    LabelTagHelper
    -0.75
    publicKey
    -0.74
    SqlClient
    -0.73
    POSITIVE LOGITS
     Off
    2.04
     off
    1.93
     OFF
    1.92
    Off
    1.86
    off
    1.77
    OFF
    1.67
     offs
    1.49
    offs
    1.43
    オフ
    1.11
     ऑफ
    1.03
    Act Density 0.050%

    No Known Activations