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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases highlighting differences in value or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isini
    -0.17
    erde
    -0.14
    forman
    -0.14
    лаÑĪ
    -0.14
    adan
    -0.13
    _via
    -0.13
    ยà¸ĩ
    -0.13
    efa
    -0.13
    agas
    -0.13
     наÑĤÑĥ
    -0.12
    POSITIVE LOGITS
     compared
    0.98
     compare
    0.74
     Compared
    0.69
     relative
    0.69
    comp
    0.66
     compares
    0.63
     comparing
    0.59
    relative
    0.58
     Compare
    0.57
    compare
    0.56
    Act Density 0.504%

    No Known Activations