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

    Neuronpedia

    INDEX
    Explanations

    non-empty lists or collections in programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     walls
    -0.63
    LEncoder
    -0.59
     tartalomajánló
    -0.58
    ymal
    -0.58
    -+
    -0.58
    tlere
    -0.56
    amur
    -0.56
    łby
    -0.55
    antism
    -0.55
     Kort
    -0.55
    POSITIVE LOGITS
    InjectAttribute
    0.80
    ftagPool
    0.72
    ]")]
    0.67
    ьаж
    0.65
    sizeCache
    0.61
    UnknownFields
    0.61
    Demografía
    0.57
     nyelven
    0.55
    }]);
    0.55
    .
    0.55
    Act Density 0.200%

    No Known Activations