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

    Neuronpedia

    INDEX
    Explanations

    numbers and special formatting elements, indicating sequences or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.82
     EconPapers
    -0.80
    enterOuterAlt
    -0.80
    GeneratedCode
    -0.78
    Personensuche
    -0.76
    InjectAttribute
    -0.74
    Personendaten
    -0.74
    .*")]
    -0.74
    FunctionFlags
    -0.71
     nakalista
    -0.71
    POSITIVE LOGITS
    <bos>
    0.49
     Anſ
    0.49
    stdc
    0.45
     respectivamente
    0.42
    }\]
    0.41
    eu
    0.40
    was
    0.40
     ſeveral
    0.39
     peeps
    0.39
     Reſ
    0.39
    Act Density 0.028%

    No Known Activations