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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of substitution or alternatives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.43
    majánló
    -1.10
    parsedMessage
    -1.05
     FetchType
    -1.05
     صوتيه
    -1.02
    <unused43>
    -1.02
    <unused41>
    -1.02
    <unused47>
    -1.01
    <unused42>
    -1.01
    <unused17>
    -1.01
    POSITIVE LOGITS
     substitute
    1.03
     substituted
    0.63
    substitute
    0.59
     substituting
    0.57
     Substitute
    0.56
     sustitu
    0.56
     substitutes
    0.52
     Ersatz
    0.49
     replaced
    0.48
    Substitute
    0.48
    Act Density 0.156%

    No Known Activations