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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with quantities or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atche
    -0.78
    rase
    -0.72
    Marie
    -0.66
    ase
    -0.65
     Hiro
    -0.65
    XXX
    -0.63
    ADA
    -0.61
    zona
    -0.61
    hyde
    -0.59
    Mos
    -0.59
    POSITIVE LOGITS
     56
    2.65
     55
    2.60
     57
    2.57
     54
    2.54
     53
    2.46
     58
    2.41
     59
    2.33
     52
    2.28
     61
    2.12
     51
    2.10
    Act Density 0.051%

    No Known Activations