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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate growth, contrast, and significant changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sole
    -0.17
    ospace
    -0.16
    kup
    -0.15
    ausal
    -0.15
    ULAR
    -0.15
    unj
    -0.14
    UIStoryboardSegue
    -0.14
    æīĭãĤĴ
    -0.14
    ument
    -0.14
     meant
    -0.13
    POSITIVE LOGITS
     contrast
    0.29
     Contrast
    0.25
    contrast
    0.24
     compared
    0.21
     contrasts
    0.20
     unlike
    0.17
     Unlike
    0.16
    Unlike
    0.15
    issy
    0.15
     opposite
    0.15
    Act Density 0.099%

    No Known Activations