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

    Neuronpedia

    INDEX
    Explanations

    specific alphanumeric codes or labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.31
     ―――――
    -1.30
    BibitemShut
    -1.22
     purpoſe
    -1.21
     themſelves
    -1.20
     pleaſure
    -1.20
     ་་
    -1.14
     Anſ
    -1.13
     Monfieur
    -1.12
    ſelves
    -1.12
    POSITIVE LOGITS
    AsUp
    0.72
     demais
    0.71
     s
    0.70
     C
    0.70
     alimentaires
    0.69
    b
    0.68
     K
    0.68
     nocy
    0.67
     P
    0.67
    j
    0.67
    Act Density 0.984%

    No Known Activations