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

    Neuronpedia

    INDEX
    Explanations

    adverbs related to absolute conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     partially
    -0.18
     slightly
    -0.18
     helt
    -0.16
     partly
    -0.16
     greatly
    -0.15
     merely
    -0.15
     somewhat
    -0.15
     very
    -0.15
    iated
    -0.14
    ứ
    -0.14
    POSITIVE LOGITS
     different
    0.23
     opposite
    0.21
     unrelated
    0.21
     unlike
    0.20
    ä¸įåIJĮçļĦ
    0.19
     separate
    0.19
     devoid
    0.18
     ÙħتÙģ
    0.17
     seperate
    0.17
     à¤ħलà¤Ĺ
    0.17
    Act Density 0.059%

    No Known Activations