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

    Neuronpedia

    INDEX
    Explanations

    negations and quantities within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    418
    -0.15
     Fior
    -0.15
    anje
    -0.15
    ARRIER
    -0.14
    ARD
    -0.14
     ActionTypes
    -0.14
    OUNDS
    -0.14
    krv
    -0.14
     vendor
    -0.14
     Vendor
    -0.14
    POSITIVE LOGITS
    aln
    0.18
    áln
    0.17
    agna
    0.16
    æľºåħ³
    0.16
    alte
    0.14
    igu
    0.14
    ayıp
    0.14
    egal
    0.14
    arch
    0.14
     Roths
    0.14
    Act Density 0.003%

    No Known Activations