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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating extremity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the extent or limits of actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nep
    -0.67
     Came
    -0.66
     Tsukuyomi
    -0.65
    rio
    -0.64
     waning
    -0.63
    depend
    -0.63
     impending
    -0.62
     Halls
    -0.61
    etta
    -0.61
     Puppet
    -0.60
    POSITIVE LOGITS
     lengths
    0.88
     redef
    0.79
     blindly
    0.74
    irtual
    0.72
     boldly
    0.71
     bashing
    0.69
    raviolet
    0.67
    linger
    0.66
    WARD
    0.63
    ãĥ¼ãĤ¯
    0.62
    Act Density 0.087%

    No Known Activations