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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases expressing limitations or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üb
    -0.16
    inos
    -0.15
     непÑĢи
    -0.14
    обÑĢаз
    -0.14
    842
    -0.14
     tÆ°Æ¡ng
    -0.14
    ledged
    -0.14
     nowhere
    -0.13
    bare
    -0.13
    esine
    -0.13
    POSITIVE LOGITS
     just
    0.30
     limited
    0.28
     merely
    0.28
     exclusive
    0.27
     rocket
    0.25
     JUST
    0.25
     about
    0.24
     simply
    0.24
     only
    0.23
    rocket
    0.23
    Act Density 0.162%

    No Known Activations