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

    Neuronpedia

    INDEX
    Explanations

    references to animals and their interactions with humans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickle
    -0.17
    pig
    -0.16
     Cater
    -0.16
     Boyd
    -0.15
    gh
    -0.15
     cater
    -0.14
     frog
    -0.14
     pigs
    -0.14
    889
    -0.14
     stagnant
    -0.14
    POSITIVE LOGITS
     Roths
    0.15
     improvis
    0.15
    ella
    0.15
    kest
    0.14
     mange
    0.14
    ÐĬ
    0.14
    /inet
    0.14
     improvised
    0.14
    ê
    0.14
     molt
    0.14
    Act Density 0.079%

    No Known Activations