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

    Neuronpedia

    INDEX
    Explanations

    expectations and comparisons between different situations or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express expectations or anticipations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anski
    -0.66
    alde
    -0.65
    ife
    -0.64
    aunder
    -0.62
    acca
    -0.62
    tein
    -0.62
    hops
    -0.62
     dehyd
    -0.61
    affe
    -0.61
     rings
    -0.61
    POSITIVE LOGITS
     payoff
    0.77
    ©¶æ
    0.74
     outcome
    0.73
     arrival
    0.69
     forgiveness
    0.67
     reaction
    0.67
     backlash
    0.66
    icipated
    0.65
    SpaceEngineers
    0.64
     audience
    0.64
    Act Density 0.166%

    No Known Activations