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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons and contrasts in situations or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AO
    -0.18
    onya
    -0.17
    uchi
    -0.16
    andum
    -0.16
    ös
    -0.15
     AO
    -0.14
    ìĦł
    -0.14
    uba
    -0.14
    strup
    -0.14
    नल
    -0.14
    POSITIVE LOGITS
    Clickable
    0.15
     Attribute
    0.14
    _utf
    0.14
    528
    0.14
    ius
    0.14
    éĸ
    0.14
    .scalablytyped
    0.14
    Attribute
    0.14
    ilter
    0.13
    atas
    0.13
    Act Density 0.049%

    No Known Activations