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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusion or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isman
    -0.15
    oron
    -0.15
    ibar
    -0.14
    .counter
    -0.14
    اکÛĮ
    -0.14
    .pattern
    -0.14
    isch
    -0.13
     AppleWebKit
    -0.13
    -counter
    -0.13
    phia
    -0.13
    POSITIVE LOGITS
     anymore
    0.19
    aha
    0.16
    ÑĢаÑī
    0.15
    ches
    0.15
     Dalton
    0.14
     actual
    0.14
     immediately
    0.14
    utions
    0.14
    126
    0.14
    stitutions
    0.14
    Act Density 0.408%

    No Known Activations