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

    Neuronpedia

    INDEX
    Explanations

    inequalities and relationships between numerical quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.79
     purpoſe
    -0.77
     ſen
    -0.75
     Conſ
    -0.74
     Reſ
    -0.72
     Jefus
    -0.72
    tagHelperRunner
    -0.71
     Jurí
    -0.70
     myſelf
    -0.70
     Houſe
    -0.70
    POSITIVE LOGITS
    oredCriteria
    0.58
    WriteBarrier
    0.51
    StringLength
    0.50
     nahilalakip
    0.49
     es
    0.46
    Datuak
    0.44
    ≈
    0.44
    AdapterFactory
    0.43
    findpost
    0.41
     >::
    0.41
    Act Density 0.393%

    No Known Activations