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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of usage or utilization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.91
    ap
    -0.71
    ru
    -0.70
     Stearns
    -0.69
     }}>
    -0.69
    ob
    -0.68
     Nellie
    -0.68
    oat
    -0.68
     Burbank
    -0.67
    oe
    -0.67
    POSITIVE LOGITS
     Utilizing
    1.01
     utilizing
    0.99
     saites
    0.99
     whilst
    0.99
     amongst
    0.96
     Whilst
    0.96
     utilize
    0.94
    Whilst
    0.94
     Firstly
    0.92
     Amongst
    0.92
    Act Density 0.149%

    No Known Activations