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

    Neuronpedia

    INDEX
    Explanations

    phrases related to winning or losing streaks in sports or competitive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocre
    -0.15
    resco
    -0.14
    ÏģÏī
    -0.14
    Split
    -0.13
    inite
    -0.13
     Hang
    -0.13
    039
    -0.13
     Jackson
    -0.13
    RAND
    -0.13
    679
    -0.13
    POSITIVE LOGITS
     streak
    0.61
     run
    0.38
     string
    0.31
     stretch
    0.30
    run
    0.29
    Run
    0.27
     Run
    0.27
    stretch
    0.26
    -run
    0.26
    .run
    0.25
    Act Density 0.162%

    No Known Activations