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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or highlight specific information or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldom
    -0.16
    /umd
    -0.15
    owards
    -0.15
    éļľ
    -0.15
    ello
    -0.15
    borg
    -0.15
    ãĥªãĥ¼ãĤº
    -0.14
    .this
    -0.14
    venes
    -0.14
    irm
    -0.14
    POSITIVE LOGITS
    ise
    0.18
    à¹Ħว
    0.17
    ìĦľëĬĶ
    0.17
    ina
    0.16
    467
    0.14
     opportunity
    0.14
    after
    0.14
    INA
    0.14
    instead
    0.14
    íĨ
    0.14
    Act Density 0.041%

    No Known Activations