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

    Neuronpedia

    INDEX
    Explanations

    legal and geopolitical information

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.75
    igo
    -0.64
    OY
    -0.61
    =-=-=-=-=-=-=-=-
    -0.60
    Finish
    -0.59
    ========
    -0.59
    omed
    -0.59
    orno
    -0.59
    okin
    -0.59
    itia
    -0.58
    POSITIVE LOGITS
    uits
    0.81
    imentary
    0.69
    taboola
    0.66
     Ltd
    0.62
    tains
    0.59
    poons
    0.59
     Bethlehem
    0.57
    CLASSIFIED
    0.56
    lishes
    0.56
    lication
    0.55
    Act Density 0.067%

    No Known Activations