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

    Neuronpedia

    INDEX
    Explanations

    commands or steps related to technical instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     incess
    -0.92
     notori
    -0.86
     sensibili
    -0.86
     liev
    -0.85
     attes
    -0.80
     solidar
    -0.80
     alkoh
    -0.77
     Chá
    -0.76
     mait
    -0.75
     dè
    -0.75
    POSITIVE LOGITS
     onto
    1.32
     into
    1.17
    into
    0.89
     vào
    0.81
    Into
    0.79
     INTO
    0.75
     Into
    0.74
    onto
    0.72
     unto
    0.64
     alongside
    0.63
    Act Density 0.568%

    No Known Activations