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

    Neuronpedia

    INDEX
    Explanations

    references to professional titles or roles, particularly those related to academia or expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATUS
    -0.18
    igu
    -0.16
    Äįek
    -0.16
    acked
    -0.15
    antee
    -0.15
    ques
    -0.15
    bara
    -0.15
    quet
    -0.15
    eric
    -0.15
    주ëĬĶ
    -0.15
    POSITIVE LOGITS
    essed
    0.30
    essions
    0.28
    essional
    0.28
    anity
    0.27
    ession
    0.27
    esse
    0.26
    iciency
    0.25
    ess
    0.25
    esso
    0.24
    iling
    0.24
    Act Density 0.011%

    No Known Activations