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

    Neuronpedia

    INDEX
    Explanations

    references to religious figures or terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ately
    -0.15
    ีà¹ī
    -0.15
    uning
    -0.15
    SizeMode
    -0.15
    OTH
    -0.14
    atomy
    -0.14
    eria
    -0.14
    zet
    -0.14
    pla
    -0.14
    aneously
    -0.14
    POSITIVE LOGITS
    ving
    0.26
     rev
    0.23
    ved
    0.21
    italize
    0.20
    ival
    0.20
    olved
    0.20
    amped
    0.20
    olutions
    0.20
    amp
    0.20
    ital
    0.20
    Act Density 0.013%

    No Known Activations