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

    Neuronpedia

    INDEX
    Explanations

    words related to chemical compounds and elements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     condem
    -0.67
     BEFORE
    -0.54
     horizont
    -0.54
    .–
    -0.53
    DEF
    -0.53
    advertisement
    -0.52
     tyr
    -0.52
    Wi
    -0.51
    Enjoy
    -0.51
    ements
    -0.51
    POSITIVE LOGITS
    chard
    1.09
    ifice
    1.04
    chid
    0.97
    phan
    0.92
    ouple
    0.87
    acle
    0.87
    GAN
    0.86
     two
    0.85
    lando
    0.83
    ific
    0.83
    Act Density 0.041%

    No Known Activations