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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "same"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apas
    -0.18
    dale
    -0.16
    inous
    -0.16
    _ABI
    -0.16
    wear
    -0.15
    xn
    -0.15
    land
    -0.14
    egot
    -0.14
    opers
    -0.14
    onaut
    -0.14
    POSITIVE LOGITS
    -sex
    0.24
    ucci
    0.17
     sterile
    0.15
    æł·
    0.15
    ymoon
    0.15
    ison
    0.14
    ediator
    0.14
    Ø·
    0.14
    -day
    0.14
    oftware
    0.14
    Act Density 0.023%

    No Known Activations