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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or actions of entering or exiting places

    oai_token-act-pair · gpt-3.5-turbo

    terms related to entering and exiting spaces or buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     graft
    -0.74
     Decay
    -0.70
    ogun
    -0.68
     marrow
    -0.65
     leukemia
    -0.65
    mpeg
    -0.64
    cancer
    -0.64
     prog
    -0.62
    DNA
    -0.62
    Percent
    -0.62
    POSITIVE LOGITS
     safely
    1.04
     downstairs
    0.92
     toilets
    0.89
     premises
    0.85
     unnoticed
    0.82
     boarded
    0.81
     peacefully
    0.81
     stairs
    0.80
     doors
    0.80
     lawfully
    0.79
    Act Density 0.265%

    No Known Activations