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

    Neuronpedia

    INDEX
    Explanations

    actions and interactions involving children and their play activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hell
    -0.16
     damned
    -0.15
     damn
    -0.15
     fucking
    -0.15
    skyt
    -0.15
    åķ
    -0.15
    Fuck
    -0.15
    shit
    -0.15
    piel
    -0.15
    indsight
    -0.14
    POSITIVE LOGITS
     mommy
    0.27
     lots
    0.21
     grown
    0.18
    ummy
    0.17
     Lots
    0.17
     pretend
    0.17
     bye
    0.16
     scary
    0.16
    eya
    0.16
     silly
    0.16
    Act Density 0.111%

    No Known Activations