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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or conditions that are happening at a certain time or in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agini
    -0.16
    жд
    -0.16
    zem
    -0.15
    ÑģÑıÑĩ
    -0.15
    ANJI
    -0.15
    grave
    -0.14
    azo
    -0.14
    تÙĥ
    -0.14
    instein
    -0.14
    ingen
    -0.14
    POSITIVE LOGITS
    est
    0.21
    íŀĪ
    0.17
    aneously
    0.17
    ement
    0.16
    ival
    0.16
    aneous
    0.15
    291
    0.15
    ness
    0.14
    /current
    0.14
    leigh
    0.13
    Act Density 0.009%

    No Known Activations