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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     inverte
    -0.65
     bolí
    -0.58
     Zelanda
    -0.57
     miniatura
    -0.56
     zumal
    -0.56
     Meksi
    -0.54
     worauf
    -0.54
     Trasp
    -0.54
     barri
    -0.52
     womit
    -0.52
    POSITIVE LOGITS
     intersper
    1.17
     apprehen
    1.01
     unlaw
    0.92
     gratify
    0.92
     encomp
    0.91
     withal
    0.91
     fortn
    0.89
     impractica
    0.88
     gaily
    0.88
     quitted
    0.86
    Act Density 0.157%

    No Known Activations