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

    Neuronpedia

    INDEX
    Explanations

    the word "such"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce or emphasize examples or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARM
    -0.76
     Mens
    -0.71
    ingham
    -0.70
    uminati
    -0.67
    IPP
    -0.66
    yard
    -0.65
     Canberra
    -0.63
    emen
    -0.63
    EL
    -0.63
    lund
    -0.63
    POSITIVE LOGITS
    iated
    0.66
     resc
    0.65
     Osw
    0.64
     matters
    0.62
     constituted
    0.60
    iqueness
    0.58
     revised
    0.58
    uman
    0.57
     unsub
    0.57
     ascert
    0.56
    Act Density 0.010%

    No Known Activations