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

    Neuronpedia

    INDEX
    Explanations

    words related to randomness or stochastic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     increí
    -0.65
     indisponible
    -0.65
    transQ
    -0.64
     Geiſt
    -0.63
    parsedMessage
    -0.63
    <unused41>
    -0.63
    <unused43>
    -0.62
    <unused68>
    -0.62
    <unused23>
    -0.62
    <unused8>
    -0.62
    POSITIVE LOGITS
     Random
    0.75
     random
    0.70
    Random
    0.67
     r
    0.66
    random
    0.62
     care
    0.58
     yield
    0.57
     The
    0.49
     Ram
    0.49
     Care
    0.47
    Act Density 0.269%

    No Known Activations