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

    Neuronpedia

    INDEX
    Explanations

    instances of comparison or conditionality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conditions or situations involving alternatives or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocracy
    -0.70
    Score
    -0.63
    then
    -0.60
    clusive
    -0.60
    est
    -0.60
    vered
    -0.60
    rous
    -0.59
    ETS
    -0.59
    onomy
    -0.58
    NOW
    -0.58
    POSITIVE LOGITS
     else
    1.09
     otherwise
    1.08
     worse
    1.06
    chard
    1.00
    acles
    0.98
     alternatively
    0.96
    nam
    0.95
    ifice
    0.90
    acle
    0.90
    Else
    0.90
    Act Density 0.123%

    No Known Activations