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

    Neuronpedia

    INDEX
    Explanations

    instances where directions are given for a specific food preparation technique

    oai_token-act-pair · gpt-3.5-turbo

    prepositions, particularly "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conom
    -0.83
    soDeliveryDate
    -0.77
    Apps
    -0.68
    urdue
    -0.66
    affe
    -0.64
    ï¸ı
    -0.63
    TPP
    -0.62
    INESS
    -0.62
    rament
    -0.61
    FF
    -0.60
    POSITIVE LOGITS
     top
    1.31
    top
    1.17
    yx
    1.10
    coming
    1.05
    eday
    0.97
    screen
    0.96
     cue
    0.96
    erous
    0.96
     opposite
    0.93
    ibaba
    0.93
    Act Density 0.116%

    No Known Activations