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

    Neuronpedia

    INDEX
    Explanations

    instances where the word 'other' is emphasized or repeated multiple times in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "other" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deliberate
    -0.65
     Catholicism
    -0.64
     soaring
    -0.63
     bis
    -0.63
     Xi
    -0.62
     clip
    -0.60
     complete
    -0.60
     pleasure
    -0.60
     rip
    -0.60
     Ferrari
    -0.59
    POSITIVE LOGITS
    swer
    1.20
    soever
    1.04
    other
    1.03
    worldly
    1.00
    wise
    1.00
    eatures
    0.97
    theless
    0.94
    sers
    0.94
    etheless
    0.93
    ypes
    0.93
    Act Density 0.006%

    No Known Activations