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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of "even" as a modifier for comparison or intensification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶļèĩ³
    -0.20
     even
    -0.19
     nawet
    -0.17
     dokonce
    -0.17
     tháºŃm
    -0.17
     sogar
    -0.15
    pper
    -0.15
     Even
    -0.15
    different
    -0.14
    /*č↵
    -0.14
    POSITIVE LOGITS
    -handed
    0.22
    ness
    0.21
    flo
    0.21
    ement
    0.20
    nia
    0.19
    ements
    0.18
    -more
    0.17
    obody
    0.17
    lope
    0.17
     Steven
    0.16
    Act Density 0.032%

    No Known Activations