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

    Neuronpedia

    INDEX
    Explanations

    references to people and their attributes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebControls
    -0.83
    IntoConstraints
    -0.72
    Personendaten
    -0.72
     typelib
    -0.66
     ProtoMessage
    -0.62
     виправивши
    -0.60
    esez
    -0.59
     religieuse
    -0.59
    MessageTagHelper
    -0.57
     étoit
    -0.57
    POSITIVE LOGITS
     never
    0.61
    TabIndex
    0.55
     seldom
    0.55
     فريبيس
    0.54
     MatDialog
    0.54
    SequentialGroup
    0.54
    bukkit
    0.53
     focused
    0.53
     capable
    0.52
     whose
    0.52
    Act Density 0.317%

    No Known Activations