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

    Neuronpedia

    INDEX
    Explanations

    the word "other" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     otherwise
    -0.20
     Otherwise
    -0.18
    cken
    -0.17
    otherwise
    -0.17
    uel
    -0.17
    Otherwise
    -0.16
     sonst
    -0.15
     lain
    -0.15
    anner
    -0.15
    rong
    -0.15
    POSITIVE LOGITS
    -than
    0.37
     than
    0.35
    world
    0.31
     niż
    0.30
    wis
    0.28
    than
    0.28
     equally
    0.28
     similarly
    0.27
    ewise
    0.26
    -world
    0.25
    Act Density 0.113%

    No Known Activations