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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific books and authors, especially related to historical figures or political topics

    oai_token-act-pair · gpt-3.5-turbo

    references to books and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mson
    -0.75
    utterstock
    -0.75
    PLIED
    -0.67
    =\"
    -0.67
    intendent
    -0.65
    ensor
    -0.65
    rower
    -0.64
    factor
    -0.63
    SI
    -0.62
     pse
    -0.62
    POSITIVE LOGITS
    Haunted
    0.90
     Babe
    0.81
     Manifest
    0.80
     Ruin
    0.77
     Dirty
    0.77
     Crus
    0.77
     Diary
    0.77
     Me
    0.77
     Overt
    0.77
     Travels
    0.76
    Act Density 0.302%

    No Known Activations