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

    Neuronpedia

    INDEX
    Explanations

    references to toys

    oai_token-act-pair · gpt-3.5-turbo

    references to toys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idency
    -0.73
    ulty
    -0.67
     transcripts
    -0.66
     inhibitors
    -0.63
    xual
    -0.61
    bleacher
    -0.61
    ignty
    -0.61
    icago
    -0.59
     probable
    -0.59
     Torrent
    -0.58
    POSITIVE LOGITS
     toys
    1.01
    ota
    0.97
    ulus
    0.96
     toy
    0.95
    slot
    0.91
    geon
    0.89
     Toys
    0.87
     Crate
    0.85
    ulo
    0.84
    glers
    0.80
    Act Density 0.025%

    No Known Activations