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

    Neuronpedia

    INDEX
    Explanations

    words that indicate contrast or comparison between different ideas or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asmus
    -0.15
    omba
    -0.15
    resa
    -0.15
    SSIP
    -0.15
    reso
    -0.14
    ngör
    -0.14
    zf
    -0.14
    ória
    -0.14
    aya
    -0.14
    ako
    -0.14
    POSITIVE LOGITS
    ester
    0.16
    776
    0.15
    oS
    0.14
    fixture
    0.14
    太éĥİ
    0.14
     equally
    0.14
     Bell
    0.14
     Jenner
    0.14
     Patt
    0.14
    åīĩ
    0.14
    Act Density 2.388%

    No Known Activations