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

    Neuronpedia

    INDEX
    Explanations

    the word "such" followed by a significant term

    oai_token-act-pair · gpt-3.5-turbo

    the word "such" as it relates to emphasizing examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.80
    ertodd
    -0.79
    emale
    -0.76
    achus
    -0.76
    icka
    -0.75
    kick
    -0.75
    oil
    -0.74
    hene
    -0.72
    opian
    -0.71
    ellen
    -0.70
    POSITIVE LOGITS
     matters
    0.80
    ties
    0.77
     kinds
    0.76
     drastic
    0.73
     heinous
    0.73
     sorts
    0.71
     establishments
    0.71
     minded
    0.70
     atro
    0.69
     mundane
    0.69
    Act Density 0.045%

    No Known Activations