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

    Neuronpedia

    INDEX
    Explanations

    references to organizational names or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     those
    -0.69
    ########.
    -0.62
    KommentareTeilen
    -0.62
     quello
    -0.62
    those
    -0.61
     theirs
    -0.58
     their
    -0.58
     respectively
    -0.57
     the
    -0.57
    的那
    -0.56
    POSITIVE LOGITS
     aim
    1.17
     goal
    1.09
     purpose
    1.01
     objective
    0.99
    目的是
    0.94
     total
    0.89
     following
    0.84
     objetivo
    0.83
     bedo
    0.82
     highlight
    0.82
    Act Density 0.550%

    No Known Activations