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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or conditions involving distance or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apro
    -0.17
    edl
    -0.16
    ishly
    -0.15
    ven
    -0.14
    bove
    -0.14
    adora
    -0.14
    acz
    -0.14
    inas
    -0.14
     -------------------------------------------------------------------------
    -0.14
    nun
    -0.13
    POSITIVE LOGITS
     concerned
    0.69
     concern
    0.50
     concerns
    0.45
     Concern
    0.44
    Concern
    0.42
     concerning
    0.27
    cern
    0.26
     preocup
    0.26
    èĢĮ
    0.25
     каÑģ
    0.23
    Act Density 0.019%

    No Known Activations