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

    Neuronpedia

    INDEX
    Explanations

    sentences starting with the token "<bos>"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vij
    -0.62
     tartalomajánló
    -0.61
     downvoted
    -0.60
    arion
    -0.60
     Hinton
    -0.60
    >−
    -0.59
    rification
    -0.59
    choon
    -0.59
     McCon
    -0.59
    রণ
    -0.58
    POSITIVE LOGITS
    enumi
    0.78
    bootstrapcdn
    0.75
    </i>
    0.73
    </em>
    0.72
    ]")]
    0.69
    EndContext
    0.68
     DialogInterface
    0.66
     الحره
    0.65
    </td>
    0.64
    ctrica
    0.64
    Act Density 0.002%

    No Known Activations