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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or comparisons involving the concept of distance or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acz
    -0.16
    ishly
    -0.16
    apro
    -0.15
    edl
    -0.15
    bove
    -0.15
    uito
    -0.14
    ven
    -0.14
    adora
    -0.14
    vens
    -0.14
    aland
    -0.14
    POSITIVE LOGITS
     concerned
    0.64
     concern
    0.46
     Concern
    0.42
     concerns
    0.41
    Concern
    0.39
    cern
    0.24
    èĢĮ
    0.24
     concerning
    0.24
     preocup
    0.24
     каÑģ
    0.22
    Act Density 0.033%

    No Known Activations