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

    Neuronpedia

    INDEX
    Explanations

    instances of change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isko
    -0.14
    arcer
    -0.13
    uzu
    -0.13
    ournaments
    -0.13
    illis
    -0.13
    enberg
    -0.13
    urum
    -0.12
    ymm
    -0.12
    ursal
    -0.12
    EXTERN
    -0.12
    POSITIVE LOGITS
     again
    1.68
    again
    1.51
     Again
    1.39
    Again
    1.35
     AGAIN
    1.07
     wieder
    1.05
     novamente
    1.04
    AGAIN
    1.01
    _again
    0.98
    åĨį
    0.90
    Act Density 1.989%

    No Known Activations