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

    Neuronpedia

    INDEX
    Explanations

    words related to financial amounts and toys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.58
     Houſe
    -1.58
     myſelf
    -1.57
     Majefty
    -1.50
     houſe
    -1.50
     Theſe
    -1.45
    ſelves
    -1.42
     pleaſure
    -1.41
     Jefus
    -1.41
     Anſ
    -1.40
    POSITIVE LOGITS
     &
    0.98
     "
    0.85
     
    0.84
      
    0.83
     in
    0.82
    ↵
    0.78
     or
    0.75
     and
    0.74
     et
    0.69
     on
    0.68
    Act Density 0.146%

    No Known Activations