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

    Neuronpedia

    INDEX
    Explanations

    terms related to critique and commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.71
     geisti
    -0.43
    jores
    -0.43
    cimentos
    -0.43
    DECREF
    -0.41
    htë
    -0.41
    ணை
    -0.41
    şekkür
    -0.40
     مرئيه
    -0.39
     lievito
    -0.39
    POSITIVE LOGITS
     unaltered
    0.99
     unmodified
    0.93
     direct
    0.91
     Direct
    0.90
     straightforward
    0.89
    Direct
    0.88
    direct
    0.87
    DIRECT
    0.87
    そのまま
    0.86
     raw
    0.86
    Act Density 0.531%

    No Known Activations