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

    Neuronpedia

    INDEX
    Explanations

    phrases reflecting uncertainty or skepticism towards statements or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¢
    -0.15
    olk
    -0.15
     Franco
    -0.15
    oleon
    -0.15
    ITHER
    -0.14
    DITION
    -0.14
    ж
    -0.14
    amba
    -0.14
    VertexBuffer
    -0.14
    illez
    -0.14
    POSITIVE LOGITS
     does
    0.28
     did
    0.27
    does
    0.22
     Does
    0.21
     DOES
    0.20
     do
    0.19
     DID
    0.18
    Does
    0.18
     Did
    0.17
    did
    0.17
    Act Density 0.218%

    No Known Activations