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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing disapproval or surprise

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disbelief or disappointment regarding situations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.81
    aukee
    -0.78
    orage
    -0.77
    ãĥ¼ãĤ¯
    -0.71
    iaz
    -0.70
    tails
    -0.70
    iHUD
    -0.70
    ä¹
    -0.68
    æĿ
    -0.67
    vc
    -0.67
    POSITIVE LOGITS
     someone
    1.08
     somebody
    0.98
     anyone
    0.93
     they
    0.87
     nobody
    0.85
     we
    0.82
    someone
    0.81
     anybody
    0.81
     people
    0.74
     THEY
    0.73
    Act Density 0.107%

    No Known Activations