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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contextual references or the scope of discussion in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     åt
    -0.66
     AttributeSet
    -0.64
    addPreferredGap
    -0.60
     préfé
    -0.59
     دى
    -0.56
    %)$
    -0.54
     âmes
    -0.54
    Exhibit
    -0.54
    inescent
    -0.53
     προς
    -0.53
    POSITIVE LOGITS
     contexts
    0.75
     context
    0.71
     contexto
    0.71
     epidemics
    0.68
     contexte
    0.67
    Portail
    0.65
     confines
    0.64
    tableFuture
    0.63
     contesto
    0.63
     prefent
    0.63
    Act Density 0.019%

    No Known Activations