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

    Neuronpedia

    INDEX
    Explanations

    words related to expectation and comparison

    oai_token-act-pair · gpt-3.5-turbo

    expectations and comparisons regarding outcomes or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.78
    aunder
    -0.75
    alde
    -0.73
    abase
    -0.70
    AAF
    -0.69
    affe
    -0.69
    anga
    -0.69
    azeera
    -0.68
    anski
    -0.67
    itaire
    -0.65
    POSITIVE LOGITS
     payoff
    0.79
     backlash
    0.71
     outcome
    0.70
     reaction
    0.69
     upfront
    0.67
    SpaceEngineers
    0.65
     Paradise
    0.65
     reactions
    0.64
     arrival
    0.64
     boon
    0.63
    Act Density 0.192%

    No Known Activations