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

    Neuronpedia

    INDEX
    Explanations

    incomplete or fragmented sentences in multiple languages

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to emotions and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untled
    -0.88
    HOW
    -0.81
    ãĤ»
    -0.80
    advertisement
    -0.79
    irtual
    -0.77
    orescent
    -0.77
    WARE
    -0.76
    ecause
    -0.76
    8000
    -0.75
    icter
    -0.75
    POSITIVE LOGITS
     lang
    0.75
     phr
    0.74
     faire
    0.73
     decl
    0.71
     li
    0.70
     vel
    0.70
     XX
    0.69
     Ud
    0.68
     thou
    0.68
     na
    0.68
    Act Density 0.192%

    No Known Activations