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

    Neuronpedia

    INDEX
    Explanations

    concepts related to personal ownership and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     isInitialized
    -0.47
    상
    -0.46
     possibilities
    -0.46
    nus
    -0.45
    acquisto
    -0.44
    zahlen
    -0.43
    CTC
    -0.42
    ighorn
    -0.42
    sendMail
    -0.41
    Root
    -0.41
    POSITIVE LOGITS
     sendiri
    1.23
     Myself
    1.13
     myself
    1.08
     personally
    1.08
    myself
    1.05
    เอง
    1.04
     pribadi
    1.03
     myſelf
    0.99
     yourself
    0.97
     ourselves
    0.96
    Act Density 0.464%

    No Known Activations