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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "so" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.63
     eviction
    -0.62
     glances
    -0.58
    rals
    -0.58
     Mens
    -0.56
    nings
    -0.55
     Slide
    -0.55
    marks
    -0.55
     presentation
    -0.54
     slide
    -0.54
    POSITIVE LOGITS
    oths
    1.26
    bered
    1.21
    othes
    1.17
    apy
    1.10
    othe
    1.04
    oooo
    0.99
    oner
    0.97
    ooo
    0.94
    iled
    0.94
    bs
    0.93
    Act Density 0.114%

    No Known Activations