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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "punish" with varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "punish" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Airl
    -0.65
     Lang
    -0.65
     Leica
    -0.64
     algae
    -0.64
     Herz
    -0.64
     Mayo
    -0.63
     WI
    -0.62
     MLA
    -0.61
     broch
    -0.61
     Pip
    -0.61
    POSITIVE LOGITS
     punish
    3.41
     punished
    3.06
     punishing
    2.71
     punishment
    2.48
     punishments
    2.40
     penal
    1.94
     retribution
    1.78
     punishable
    1.70
     retaliate
    1.66
    pun
    1.56
    Act Density 0.027%

    No Known Activations