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

    Neuronpedia

    INDEX
    Explanations

    phrases related to books and publications

    oai_token-act-pair · gpt-3.5-turbo

    quotes around artistic works and discussions of published books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forces
    -0.73
    nel
    -0.72
     flare
    -0.72
    vous
    -0.71
    terior
    -0.71
     disconnect
    -0.70
     airspace
    -0.69
     DHCP
    -0.68
    onomous
    -0.68
    zzle
    -0.68
    POSITIVE LOGITS
     memoir
    1.16
     poems
    1.10
     essays
    1.10
     autobi
    1.07
     autobiography
    1.06
     catalogue
    1.04
     manuscript
    1.02
     textbooks
    1.01
     novels
    0.99
     journals
    0.99
    Act Density 0.294%

    No Known Activations