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

    Neuronpedia

    INDEX
    Explanations

    phrases related to journeys and experiences of progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .MSG
    -0.15
    AXB
    -0.15
    ymm
    -0.14
    YLON
    -0.13
    ynth
    -0.13
    ¥¿
    -0.13
    ournaments
    -0.13
    اشتÙĩ
    -0.12
    ardash
    -0.12
    eras
    -0.12
    POSITIVE LOGITS
     again
    1.51
    again
    1.34
     Again
    1.23
    Again
    1.20
     AGAIN
    1.00
     wieder
    0.94
    AGAIN
    0.93
     novamente
    0.92
     once
    0.92
    _again
    0.88
    Act Density 1.696%

    No Known Activations