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

    Neuronpedia

    INDEX
    Explanations

    references to family dynamics and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Explicit
    -0.16
    erb
    -0.15
    aper
    -0.15
    ipa
    -0.14
    ousse
    -0.14
    Enumerable
    -0.14
    £¼
    -0.14
     Erotic
    -0.14
    貸
    -0.13
     escort
    -0.13
    POSITIVE LOGITS
     eat
    0.59
     eating
    0.57
     consumption
    0.54
    -e
    0.54
     eats
    0.52
    Eat
    0.52
     consume
    0.51
     Consum
    0.51
     consuming
    0.50
    eating
    0.48
    Act Density 0.339%

    No Known Activations