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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transformation or modification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peper
    -0.54
    cattle
    -0.49
     Zusammen
    -0.48
    肝
    -0.47
    Coul
    -0.47
    endian
    -0.46
    setof
    -0.46
     ого
    -0.45
     Kenne
    -0.45
    "}")
    -0.45
    POSITIVE LOGITS
     become
    0.88
     deviennent
    0.85
    Become
    0.85
     diventare
    0.85
    值为
    0.82
    AnchorStyles
    0.80
     becomes
    0.79
     becoming
    0.78
     Become
    0.78
    Geplaatst
    0.75
    Act Density 0.410%

    No Known Activations