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

    Neuronpedia

    INDEX
    Explanations

    words related to support or assistance

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to dialogue and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    a
    -0.58
    an
    -0.56
    advertising
    -0.54
    ahime
    -0.53
    ine
    -0.53
    paren
    -0.52
    anus
    -0.51
    oola
    -0.50
    ayn
    -0.49
    aan
    -0.49
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.64
    iaries
    0.57
    ģ«
    0.57
    terday
    0.53
    otaur
    0.52
    utsche
    0.51
    edom
    0.51
    ²¾
    0.48
    udeb
    0.48
    olean
    0.47
    Act Density 0.533%

    No Known Activations