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

    Neuronpedia

    INDEX
    Explanations

    terms associated with falsehood or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.77
    rungsseite
    -0.67
    LookAnd
    -0.57
     typelib
    -0.56
    RectangleBorder
    -0.55
     Rakyat
    -0.54
     MainAxisSize
    -0.53
    Lähteet
    -0.52
     Portail
    -0.52
     betweenstory
    -0.51
    POSITIVE LOGITS
     false
    2.02
     False
    1.75
    false
    1.59
    False
    1.55
     FALSE
    1.22
     falsos
    1.22
     falso
    1.19
     falsa
    1.18
     falsas
    1.16
    FALSE
    1.09
    Act Density 0.140%

    No Known Activations