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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating approximation or universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.16
    claimer
    -0.15
    ogan
    -0.15
    oton
    -0.15
    elif
    -0.15
     пÑĥ
    -0.14
    å±ħ
    -0.14
    ám
    -0.14
    amental
    -0.14
    arp
    -0.14
    POSITIVE LOGITS
     exclusively
    0.25
     entirely
    0.21
     entire
    0.20
     identical
    0.18
     ëĮĢë¶Ģë¶Ħ
    0.17
     everyone
    0.17
     everything
    0.17
     complete
    0.17
     everybody
    0.17
     completely
    0.16
    Act Density 0.078%

    No Known Activations