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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups taking part in a study or program

    oai_token-act-pair · gpt-3.5-turbo

    references to participants in a study or research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vell
    -0.69
     vengeance
    -0.68
     Sense
    -0.63
     Bale
    -0.63
    flu
    -0.59
     Shack
    -0.59
    otropic
    -0.58
    asso
    -0.58
    put
    -0.58
     clich
    -0.57
    POSITIVE LOGITS
    cript
    0.91
     Participants
    0.87
    IAL
    0.77
     participant
    0.76
    particip
    0.75
    bilt
    0.75
    essee
    0.75
    hips
    0.73
     participants
    0.72
    ividual
    0.71
    Act Density 0.032%

    No Known Activations