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

    Neuronpedia

    INDEX
    Explanations

    phrases involving choices, options, or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating contrasting outcomes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    then
    -0.76
    NOW
    -0.76
    ocracy
    -0.70
    onday
    -0.66
    ails
    -0.66
    ETS
    -0.65
    Score
    -0.63
    BLIC
    -0.60
    eth
    -0.60
    arte
    -0.60
    POSITIVE LOGITS
     else
    1.25
    acles
    1.23
     otherwise
    1.21
     alternatively
    1.20
    nam
    1.19
    chard
    1.08
     worse
    1.07
    ifice
    1.06
    acle
    1.04
     simply
    1.04
    Act Density 0.163%

    No Known Activations