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

    Neuronpedia

    INDEX
    Explanations

    instances of specific food-related actions like "chopped"

    oai_token-act-pair · gpt-3.5-turbo

    words related to food preparation or cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stadt
    -0.77
     Fargo
    -0.73
    âĢİ
    -0.67
     Mulcair
    -0.67
    #$
    -0.65
     Fortress
    -0.64
    Wiki
    -0.63
    lander
    -0.63
    hof
    -0.63
    iday
    -0.62
    POSITIVE LOGITS
     planned
    0.66
    lication
    0.63
     emergence
    0.62
     implants
    0.62
    igham
    0.61
     overhe
    0.61
     intended
    0.59
     reinforcement
    0.59
     typical
    0.58
    å£
    0.57
    Act Density 0.000%

    No Known Activations