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

    Neuronpedia

    INDEX
    Explanations

    elements related to emotional depth and complexity in narrative or character descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.36
     pleaſure
    -1.29
     Monfieur
    -1.22
     reaſon
    -1.20
     Cæsar
    -1.19
     greateſt
    -1.19
     themſelves
    -1.19
    RegistryLite
    -1.16
     Theſe
    -1.15
     purpoſe
    -1.13
    POSITIVE LOGITS
     &
    0.44
     sweet
    0.43
     and
    0.42
     Can
    0.39
     po
    0.39
    ,
    0.39
     et
    0.38
     can
    0.38
    &
    0.38
     
    0.38
    Act Density 0.560%

    No Known Activations