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

    Neuronpedia

    INDEX
    Explanations

    contrasting conjunctions along with phrases indicating doubt, inquiry, or analysis

    oai_token-act-pair · gpt-3.5-turbo

    contrasting phrases or qualifiers in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nes
    -0.71
    cess
    -0.69
    umat
    -0.69
    oided
    -0.69
    ayn
    -0.67
    ion
    -0.66
    ãĥĺ
    -0.65
    break
    -0.65
    icut
    -0.65
    irm
    -0.65
    POSITIVE LOGITS
     nonetheless
    1.06
     nevertheless
    0.98
     alas
    0.79
     suffice
    0.76
     Wenger
    0.75
     underscores
    0.72
     illustrates
    0.72
     secondly
    0.72
     indicative
    0.71
     moreover
    0.71
    Act Density 0.347%

    No Known Activations