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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conversation and dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lette
    -0.16
    ubi
    -0.14
    ucken
    -0.14
    ecs
    -0.14
    stood
    -0.14
    stag
    -0.14
    ecast
    -0.14
    út
    -0.13
    apon
    -0.13
    stu
    -0.13
    POSITIVE LOGITS
    ¶Į
    0.17
    onta
    0.16
    693
    0.16
    argin
    0.15
    شتر
    0.15
    ANTA
    0.15
    é½
    0.15
    igr
    0.14
    umb
    0.14
    iers
    0.14
    Act Density 0.006%

    No Known Activations