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

    Neuronpedia

    INDEX
    Explanations

    instances where a particular action has to be done

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate obligations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĺħ
    -0.59
    fters
    -0.58
    cade
    -0.57
    uster
    -0.56
    ibliography
    -0.55
    erno
    -0.52
    SET
    -0.51
    Newsletter
    -0.51
    ovi
    -0.51
    peed
    -0.51
    POSITIVE LOGITS
     to
    1.25
     difficulty
    1.05
     trouble
    0.97
    to
    0.96
     TO
    0.86
    To
    0.83
     recourse
    0.82
     difficulties
    0.78
     problems
    0.74
     nightmares
    0.72
    Act Density 0.278%

    No Known Activations