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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a topic transition or introducing a new concept

    oai_token-act-pair · gpt-3.5-turbo

    the word "This" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pots
    -0.71
    adle
    -0.69
    ARS
    -0.67
    ãĤ¹ãĥĪ
    -0.66
    aws
    -0.62
    ãĥĺ
    -0.62
    ©¶æ¥µ
    -0.62
    imm
    -0.61
    oller
    -0.61
    aments
    -0.59
    POSITIVE LOGITS
     week
    0.82
     latest
    0.78
     arrang
    0.76
     article
    0.75
     Week
    0.74
     month
    0.73
     Month
    0.72
     trope
    0.71
     excerpt
    0.70
     discrepancy
    0.69
    Act Density 0.164%

    No Known Activations