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

    Neuronpedia

    INDEX
    Explanations

    words related to substances like sugar (represented by 'su'), regardless of the context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "su"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ferdinand
    -0.60
    forth
    -0.58
     union
    -0.57
     Union
    -0.57
     owl
    -0.57
     Noir
    -0.57
     Weir
    -0.56
     Hitchcock
    -0.56
     Lyme
    -0.55
     Ahead
    -0.55
    POSITIVE LOGITS
    fficiency
    1.31
    nder
    1.18
    zanne
    1.18
    ction
    1.08
    prisingly
    1.06
    ffic
    1.04
    cess
    1.04
    ccess
    1.01
    prise
    1.01
    itor
    0.97
    Act Density 0.012%

    No Known Activations