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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hastly
    -0.71
     nera
    -0.70
     cabrio
    -0.65
     chod
    -0.63
    appartement
    -0.61
     maroc
    -0.61
    lastonbury
    -0.61
     appartamento
    -0.59
     sprocket
    -0.58
     camere
    -0.58
    POSITIVE LOGITS
     Præ
    0.76
     Souha
    0.73
     Că
    0.72
     whither
    0.71
     NUKAT
    0.69
     intrigu
    0.68
     gaily
    0.67
     Ră
    0.67
     vagu
    0.66
    %\[
    0.65
    Act Density 0.125%

    No Known Activations