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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing negation or absence regarding established knowledge or conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.53
     Clube
    -0.45
    diad
    -0.44
     فعل
    -0.43
     polaire
    -0.43
     preterm
    -0.43
     Avila
    -0.41
    Arcade
    -0.41
     út
    -0.40
    losigkeit
    -0.40
    POSITIVE LOGITS
     Roskov
    0.74
     autorytatywna
    0.74
    aarrggbb
    0.71
     ISNI
    0.70
    migrationBuilder
    0.69
    ChildScrollView
    0.65
     &___
    0.65
    besar
    0.60
    InitVars
    0.60
     viewDidLoad
    0.60
    Act Density 0.064%

    No Known Activations