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

    Neuronpedia

    INDEX
    Explanations

    references to books and authors

    oai_token-act-pair · gpt-3.5-turbo

    references to authorship and collaborative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inconven
    -0.63
    ppings
    -0.58
     positives
    -0.57
     retaliate
    -0.57
     unpredict
    -0.57
     overpower
    -0.56
     customs
    -0.56
     choking
    -0.55
    xit
    -0.55
    enery
    -0.55
    POSITIVE LOGITS
     scholarly
    1.07
     methodological
    0.95
     publication
    0.92
     academic
    0.89
    published
    0.89
     essays
    0.85
     scholar
    0.84
     editor
    0.83
    blog
    0.83
     editorial
    0.83
    Act Density 1.399%

    No Known Activations