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

    Neuronpedia

    INDEX
    Explanations

    references to specific actions or types of physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozo
    -0.17
    ä¸Ķ
    -0.17
     piv
    -0.14
    Truthy
    -0.14
     Deg
    -0.13
    orton
    -0.13
    ivial
    -0.13
     Bool
    -0.13
     Dear
    -0.13
     AP
    -0.13
    POSITIVE LOGITS
     afin
    0.22
     instead
    0.18
     inorder
    0.17
     ÑĩÑĤобÑĭ
    0.17
    513
    0.16
     Äijá»ĥ
    0.16
     nhằm
    0.15
    ilerden
    0.15
     because
    0.15
    instead
    0.14
    Act Density 0.180%

    No Known Activations