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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     accla
    -1.29
     reluct
    -1.23
     fuf
    -1.22
     embra
    -1.20
     inev
    -1.19
     purcha
    -1.19
     strick
    -1.16
     shenan
    -1.16
     encomp
    -1.15
     depic
    -1.13
    POSITIVE LOGITS
     seem
    0.57
     seems
    0.54
     sometimes
    0.54
     seemed
    0.54
     acknowledge
    0.54
     וגם
    0.52
    hancer
    0.51
    (!
    0.51
     nawet
    0.51
    hitheatre
    0.51
    Act Density 0.269%

    No Known Activations