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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases or expressions that indicate change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oders
    -0.15
    ivnÃŃ
    -0.15
    gon
    -0.14
    決
    -0.14
    bons
    -0.14
    oram
    -0.14
     Obt
    -0.13
    æŃ£
    -0.13
    òn
    -0.13
    ORY
    -0.13
    POSITIVE LOGITS
     otherwise
    0.19
     did
    0.17
     than
    0.17
    otherwise
    0.16
     jinak
    0.16
    mania
    0.15
    Otherwise
    0.15
     Otherwise
    0.14
    entence
    0.14
     hall
    0.14
    Act Density 0.038%

    No Known Activations