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

    Neuronpedia

    INDEX
    Explanations

    words related to utility and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.38
     prouver
    -0.37
     trovo
    -0.36
     suela
    -0.35
     Podemos
    -0.35
     habet
    -0.35
    évaluateur
    -0.34
     féminine
    -0.34
     tendenza
    -0.33
    offsetof
    -0.32
    POSITIVE LOGITS
     Utility
    0.97
     utility
    0.92
    utility
    0.84
    Utility
    0.82
    Rice
    0.79
     Rice
    0.78
     rice
    0.78
     upload
    0.72
     uploads
    0.68
     wet
    0.66
    Act Density 0.066%

    No Known Activations