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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forceful or aggressive actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rip" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MacArthur
    -0.77
    äºĶ
    -0.71
    ADRA
    -0.70
    iae
    -0.69
    avis
    -0.68
    ittees
    -0.66
     Administration
    -0.65
    OTE
    -0.63
    beit
    -0.62
    Liber
    -0.61
    POSITIVE LOGITS
     rip
    0.94
    ulously
    0.86
    adoes
    0.85
     ripped
    0.84
    rodu
    0.83
    rint
    0.82
    away
    0.81
    ulent
    0.80
     apart
    0.80
    dragon
    0.78
    Act Density 0.018%

    No Known Activations