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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasting ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĻ£
    -0.16
    alach
    -0.16
    irsch
    -0.15
    fallback
    -0.15
    quals
    -0.14
    atoi
    -0.14
     Enumerator
    -0.14
    oir
    -0.14
    dsa
    -0.14
    ICAST
    -0.13
    POSITIVE LOGITS
    ely
    0.16
    ward
    0.16
    ARD
    0.15
     ÐŁÐ¾Ð»ÑĮ
    0.14
    å°¾
    0.14
    Swap
    0.14
    Kon
    0.14
    ark
    0.13
    arde
    0.13
    aldi
    0.13
    Act Density 0.009%

    No Known Activations