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

    Neuronpedia

    INDEX
    Explanations

    various forms of contractions and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.70
     
    -0.46
    .
    -0.46
     l
    -0.45
     (
    -0.41
     im
    -0.40
    ↵
    -0.40
     den
    -0.39
     mod
    -0.38
     _
    -0.38
    POSITIVE LOGITS
     myſelf
    1.56
     itſelf
    1.55
     purpoſe
    1.53
     Majefty
    1.52
     pleaſure
    1.47
     poffible
    1.46
     raiſ
    1.45
     themſelves
    1.43
     Efq
    1.42
     poffe
    1.41
    Act Density 0.135%

    No Known Activations