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

    Neuronpedia

    INDEX
    Explanations

    references to creativity and originality in human work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.21
     Approximately
    -0.15
     ours
    -0.15
     khá
    -0.14
     approximately
    -0.14
    (?
    -0.14
     (?
    -0.13
    ilon
    -0.13
     bastante
    -0.13
     mostly
    -0.13
    POSITIVE LOGITS
     suddenly
    0.23
     tomorrow
    0.22
     XYZ
    0.22
     tÅĻeba
    0.21
    çªģçĦ¶
    0.20
    æŁIJ
    0.19
     someone
    0.18
     завÑĤÑĢа
    0.18
     say
    0.18
     somebody
    0.18
    Act Density 1.010%

    No Known Activations