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

    Neuronpedia

    INDEX
    Explanations

    references to switches and switch-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.40
    ️
    -0.37
    XmlElement
    -0.34
    SizeF
    -0.33
     ko
    -0.33
    ynı
    -0.33
     Ko
    -0.32
     gekomen
    -0.31
     McCa
    -0.31
     sisa
    -0.31
    POSITIVE LOGITS
     Switch
    0.90
     Switches
    0.78
     SWITCH
    0.76
    Switch
    0.75
     switch
    0.75
     switches
    0.73
    SWITCH
    0.72
    switch
    0.66
     switched
    0.63
     スイッチ
    0.63
    Act Density 0.103%

    No Known Activations