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

    Neuronpedia

    INDEX
    Explanations

    phrases related to one-on-one interactions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tex
    -0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    ģĸ
    -0.72
    Ĥª
    -0.70
    eah
    -0.67
    Writer
    -0.67
    States
    -0.66
    SHARE
    -0.66
    Writ
    -0.66
    TPS
    -0.65
    POSITIVE LOGITS
    etheless
    1.29
    coming
    1.20
    slaught
    0.93
     arrival
    0.89
    etime
    0.88
    itored
    0.86
    auts
    0.84
     behalf
    0.84
     demand
    0.83
    assis
    0.81
    Act Density 0.055%

    No Known Activations