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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate frequency or recurrence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     altogether
    -0.16
    ats
    -0.16
    ryo
    -0.15
    ucha
    -0.15
    kaar
    -0.14
    figcaption
    -0.14
    ipple
    -0.14
    ri
    -0.14
    iet
    -0.14
    ikal
    -0.14
    POSITIVE LOGITS
     someone
    0.19
    æľī人
    0.17
    aving
    0.16
     somebody
    0.16
    anything
    0.15
    theless
    0.15
     you
    0.15
     we
    0.15
     ANY
    0.15
    gency
    0.15
    Act Density 0.019%

    No Known Activations