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

    Neuronpedia

    INDEX
    Explanations

    words related to drinks like beer

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "election" activities or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PA
    -0.63
     Getty
    -0.61
     Met
    -0.60
     matter
    -0.58
     speaking
    -0.58
     Angels
    -0.57
     ind
    -0.56
     concerned
    -0.55
     cont
    -0.54
     thin
    -0.54
    POSITIVE LOGITS
    eer
    5.29
    eers
    4.02
    eering
    3.65
    een
    1.38
    yip
    1.19
    mble
    1.10
    hare
    1.03
    eor
    0.96
    ezvous
    0.96
    emo
    0.96
    Act Density 0.018%

    No Known Activations