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

    Neuronpedia

    INDEX
    Explanations

    expressions of approval or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ůl
    -0.17
    osate
    -0.16
    ascar
    -0.16
    anca
    -0.15
    eldon
    -0.15
    Äįek
    -0.15
    ADOR
    -0.15
    į¼
    -0.14
    ISCO
    -0.14
    çĦ¶
    -0.14
    POSITIVE LOGITS
    tober
    0.30
    lahoma
    0.29
    ahoma
    0.20
    AY
    0.19
    lah
    0.18
    amoto
    0.17
    ategor
    0.17
     Springer
    0.17
     Ok
    0.16
    anagan
    0.16
    Act Density 0.035%

    No Known Activations