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

    Neuronpedia

    INDEX
    Explanations

    authors and their works

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     specificity
    -0.71
    othe
    -0.67
    ¬¼
    -0.64
    ooth
    -0.63
    tun
    -0.63
     vibrations
    -0.62
     broom
    -0.62
     technicians
    -0.61
    Enlarge
    -0.61
     vibration
    -0.60
    POSITIVE LOGITS
     memoir
    0.83
    ospels
    0.80
     bestselling
    0.75
     Cosponsors
    0.75
    olkien
    0.73
    thood
    0.73
     autobiography
    0.72
     Awakens
    0.69
     essays
    0.69
     books
    0.68
    Act Density 0.080%

    No Known Activations