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

    Neuronpedia

    INDEX
    Explanations

    terminology related to the target audience or viewers

    oai_token-act-pair · gpt-3.5-turbo

    references to an audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idy
    -0.65
    empt
    -0.65
     Baker
    -0.64
    imov
    -0.63
    borg
    -0.63
     Scot
    -0.63
    SB
    -0.61
    abases
    -0.61
    loo
    -0.59
    phalt
    -0.59
    POSITIVE LOGITS
     member
    1.08
     members
    1.03
    members
    0.93
     audience
    0.92
     tuning
    0.91
     participation
    0.91
     receptive
    0.86
     surrogate
    0.85
     tuned
    0.84
    member
    0.84
    Act Density 0.054%

    No Known Activations