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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental entities and actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ver," indicating a focus on the verb form used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.80
    Ĭ±
    -0.65
    ById
    -0.64
    ENDED
    -0.64
    akings
    -0.64
    ecause
    -0.63
    hetti
    -0.63
    awk
    -0.60
    cffffcc
    -0.60
    uncture
    -0.59
    POSITIVE LOGITS
    ver
    1.34
    dict
    1.07
    tex
    1.04
    gence
    1.01
    lisher
    1.00
    theless
    0.97
    vers
    0.92
    vier
    0.91
    ãĥ´ãĤ¡
    0.88
    izable
    0.87
    Act Density 0.005%

    No Known Activations