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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ideas and considerations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to discovery and realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UNCLASSIFIED
    -0.89
     Azerb
    -0.83
    anwhile
    -0.79
     destro
    -0.68
     pse
    -0.68
    Versions
    -0.67
     looph
    -0.67
    âķIJ
    -0.67
    )."
    -0.65
    lvl
    -0.65
    POSITIVE LOGITS
     âĢº
    0.93
    utterstock
    0.67
     âĢİ
    0.66
     hockey
    0.64
     horny
    0.63
     geek
    0.63
    yrics
    0.62
     frontman
    0.62
     superhero
    0.61
     culinary
    0.61
    Act Density 1.499%

    No Known Activations