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

    Neuronpedia

    INDEX
    Explanations

    phrases or commands prompting the user to input information or perform an action

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts for user input

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coun
    -0.71
     laundering
    -0.67
    acca
    -0.67
     jud
    -0.65
    ector
    -0.62
     overr
    -0.61
     judgement
    -0.60
     fairness
    -0.58
    fml
    -0.58
     conviction
    -0.58
    POSITIVE LOGITS
    prise
    1.29
    prises
    1.26
    tain
    1.07
    tainment
    1.03
    taining
    1.03
    Enter
    1.03
    prising
    0.99
     Enter
    0.97
    tis
    0.87
    igible
    0.82
    Act Density 0.006%

    No Known Activations