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

    Neuronpedia

    INDEX
    Explanations

    references to reductions or decreases in quantity or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nhật
    -0.54
    PERFORMANCE
    -0.53
    weights
    -0.53
     adil
    -0.52
     cancelamento
    -0.49
    ις
    -0.48
    Exception
    -0.48
    levelse
    -0.47
    kev
    -0.46
    celi
    -0.46
    POSITIVE LOGITS
    1.13
     ſche
    1.08
    Portail
    1.01
     Theſe
    0.90
     raiſ
    0.90
     ultimately
    0.89
     ſever
    0.84
     deſt
    0.83
     ſeveral
    0.83
     whoſe
    0.82
    Act Density 0.129%

    No Known Activations