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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a shift in focus or a new point in a text

    oai_token-act-pair · gpt-3.5-turbo

    the word "again" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELD
    -0.67
    ady
    -0.67
    RNA
    -0.62
    ighed
    -0.62
    ENN
    -0.59
     agency
    -0.59
    ULAR
    -0.58
    atlantic
    -0.57
    conom
    -0.56
    ÅĤ
    -0.56
    POSITIVE LOGITS
     yeah
    1.15
     please
    1.06
     yes
    0.98
     alas
    0.95
     beware
    0.90
     congr
    0.89
     PLEASE
    0.88
     thank
    0.86
     uh
    0.83
    icio
    0.82
    Act Density 0.252%

    No Known Activations