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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses starting with the word "which"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.86
     Bed
    -0.75
    politics
    -0.74
     Bedford
    -0.65
     Tanz
    -0.65
    MENTS
    -0.65
    STE
    -0.62
    let
    -0.61
     Baker
    -0.61
     Anything
    -0.60
    POSITIVE LOGITS
    soever
    0.91
     resulted
    0.86
     comprises
    0.85
     enables
    0.79
     brings
    0.78
     incidentally
    0.78
     exposes
    0.78
     contains
    0.77
     includes
    0.77
    iao
    0.76
    Act Density 0.083%

    No Known Activations