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

    Neuronpedia

    INDEX
    Explanations

    references to broadcasting activities or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "broadcast."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urat
    -0.77
    uana
    -0.72
    tesy
    -0.71
    ugs
    -0.69
    illard
    -0.68
    atche
    -0.66
    pton
    -0.66
    appy
    -0.66
     heels
    -0.65
    othes
    -0.64
    POSITIVE LOGITS
     Broadcast
    1.19
     broadcast
    1.08
    casters
    1.03
     broadcasters
    0.93
     broadcasts
    0.90
     broadcasting
    0.89
     broadcaster
    0.84
    é¾
    0.84
    éŃĶ
    0.82
     Broadcasting
    0.81
    Act Density 0.011%

    No Known Activations