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

    Neuronpedia

    INDEX
    Explanations

    adverbs or phrases indicating degree or certainty/specificity

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izont
    -0.76
    ittal
    -0.69
    odic
    -0.67
    indal
    -0.66
    nikov
    -0.65
    ivating
    -0.62
    peria
    -0.62
    hern
    -0.62
    arter
    -0.61
     Doing
    -0.61
    POSITIVE LOGITS
     resembled
    1.06
     resembles
    1.04
     belonged
    1.04
     existed
    0.97
     lasted
    0.95
     translates
    0.92
     derives
    0.92
     earns
    0.91
     dominates
    0.90
     lacked
    0.90
    Act Density 0.166%

    No Known Activations