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

    Neuronpedia

    INDEX
    Explanations

    email addresses and Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of online platforms and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.77
     Scheme
    -0.76
     Stall
    -0.72
     Patron
    -0.69
     Rahman
    -0.68
     Sexy
    -0.68
     Exercise
    -0.67
    Grade
    -0.67
     Pupp
    -0.67
     Mandela
    -0.66
    POSITIVE LOGITS
    archives
    0.90
    ipeg
    0.89
    nexus
    0.88
    foundation
    0.86
    ribune
    0.85
    medi
    0.85
    journal
    0.84
    chron
    0.82
    biz
    0.81
    weekly
    0.81
    Act Density 0.079%

    No Known Activations