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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "blocked" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shown
    -0.78
    rift
    -0.76
    present
    -0.73
    eah
    -0.73
     nucleus
    -0.71
    kind
    -0.69
    gain
    -0.68
    matically
    -0.67
     pleasing
    -0.67
    rious
    -0.66
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.80
    ĵĺ
    0.76
     Lists
    0.63
    ogging
    0.63
    iard
    0.63
     Susp
    0.62
    adoes
    0.61
    ishment
    0.61
    pedia
    0.61
    buster
    0.60
    Act Density 0.026%

    No Known Activations