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

    Neuronpedia

    INDEX
    Explanations

    verbs related to changes or lack of changes

    oai_token-act-pair · gpt-3.5-turbo

    statements about change and its impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.73
    ortment
    -0.69
    oided
    -0.63
    arenthood
    -0.61
    isha
    -0.60
     spun
    -0.59
    çĦ
    -0.58
    igham
    -0.58
    ãĤ¹ãĥĪ
    -0.56
     Pax
    -0.56
    POSITIVE LOGITS
     whatsoever
    1.23
     nor
    1.12
     anymore
    0.95
     except
    0.90
    SPONSORED
    0.90
     slightest
    0.77
    nor
    0.77
    nil
    0.76
     anybody
    0.74
     anything
    0.73
    Act Density 0.080%

    No Known Activations