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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and policy contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "'
    -0.54
    ={`/
    -0.54
    ("/
    -0.52
     []*
    -0.51
    /*
    -0.50
    ="/"
    -0.50
     `"
    -0.50
    ("*
    -0.50
    равда
    -0.50
     ["
    -0.49
    POSITIVE LOGITS
    StructEnd
    0.86
    oa̍t
    0.80
    ConstraintMaker
    0.78
     CreateTagHelper
    0.76
     beginnetje
    0.74
     فريبيس
    0.73
    PerformLayout
    0.72
    IntoConstraints
    0.71
    AnimationsModule
    0.71
     Chwiliwch
    0.70
    Act Density 7.074%

    No Known Activations