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

    Neuronpedia

    INDEX
    Explanations

    technical formatting or structural elements in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.87
     faſt
    -0.81
    SharedCtor
    -0.80
     iſt
    -0.80
     greateſt
    -0.76
     ſch
    -0.76
     SwitchCompat
    -0.75
     ſind
    -0.74
     juſ
    -0.73
    ſelves
    -0.73
    POSITIVE LOGITS
     
    0.77
     Other
    0.73
     second
    0.73
    Other
    0.70
     other
    0.70
     drugi
    0.63
    other
    0.63
     third
    0.60
     deuxième
    0.59
    second
    0.59
    Act Density 0.937%

    No Known Activations