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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or criticism in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    996
    -0.17
    533
    -0.17
    534
    -0.16
    YTE
    -0.15
    573
    -0.15
    abo
    -0.15
    673
    -0.15
     Philips
    -0.14
    vers
    -0.14
    ason
    -0.14
    POSITIVE LOGITS
    oner
    0.15
     Pf
    0.14
     Royal
    0.14
    efon
    0.14
    ADOR
    0.13
     Lal
    0.13
    ãģªãĤĭ
    0.13
     guilty
    0.13
    ated
    0.13
    Doctrine
    0.13
    Act Density 0.021%

    No Known Activations