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

    Neuronpedia

    INDEX
    Explanations

    terms related to being confined or stored away

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.80
    ArrowToggle
    -0.77
     pamamagitan
    -0.73
     Réponses
    -0.72
    PerformLayout
    -0.72
     pleaſure
    -0.71
    حياته
    -0.70
     raiſ
    -0.69
     kautta
    -0.68
    RegressionTest
    -0.68
    POSITIVE LOGITS
     somewhere
    0.97
    somewhere
    0.81
     inside
    0.77
     firmly
    0.71
     someplace
    0.70
     tight
    0.68
    Somewhere
    0.68
     tightly
    0.68
     Somewhere
    0.67
     among
    0.67
    Act Density 0.423%

    No Known Activations