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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and commands in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſeveral
    -1.13
     myſelf
    -1.12
     pleaſure
    -1.10
    ſelves
    -1.08
     ſtate
    -1.06
     uſe
    -1.04
    thâu
    -1.03
    IsMutable
    -1.03
     itſelf
    -1.00
    ſelf
    -1.00
    POSITIVE LOGITS
     &
    0.62
     and
    0.59
     or
    0.57
    /
    0.56
    _
    0.56
      
    0.55
     _
    0.52
     et
    0.48
     vs
    0.47
     ____
    0.47
    Act Density 1.090%

    No Known Activations