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

    Neuronpedia

    INDEX
    Explanations

    opinions or personal experiences described with emphasis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     EEU
    -0.81
     PLW
    -0.81
     Punj
    -0.69
     Gaut
    -0.68
     unlaw
    -0.66
     Keny
    -0.63
     Sted
    -0.63
     BSEB
    -0.62
     philanth
    -0.61
     Intere
    -0.61
    POSITIVE LOGITS
     ever
    0.78
     EVER
    0.72
    EVER
    0.61
     jemals
    0.58
     Mère
    0.58
     perles
    0.58
     Romains
    0.57
    Autoritní
    0.57
    iconque
    0.57
     gardien
    0.57
    Act Density 0.111%

    No Known Activations