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

    Neuronpedia

    INDEX
    Explanations

    terms associated with knowledge or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritt
    -0.16
    rana
    -0.15
    orgh
    -0.15
    NCY
    -0.14
    GLOSS
    -0.14
    itler
    -0.14
    riba
    -0.14
    olina
    -0.14
    elerinden
    -0.13
    PIO
    -0.13
    POSITIVE LOGITS
     simply
    0.26
     collo
    0.24
     inform
    0.24
    s
    0.23
     col
    0.22
     popular
    0.21
     affection
    0.20
     loving
    0.20
     gener
    0.19
     various
    0.19
    Act Density 0.028%

    No Known Activations