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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight differences between items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alia
    -0.15
    alli
    -0.15
    leur
    -0.15
    .mit
    -0.15
    ideo
    -0.14
    opia
    -0.14
    lique
    -0.14
     Pell
    -0.14
    еÑģÑĮ
    -0.14
    eth
    -0.13
    POSITIVE LOGITS
    ê¶Į
    0.17
    OOM
    0.16
    TL
    0.15
    <j
    0.15
    cales
    0.14
    ingleton
    0.14
    .simple
    0.14
     Felix
    0.14
    labs
    0.14
    ventus
    0.14
    Act Density 0.060%

    No Known Activations