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

    Neuronpedia

    INDEX
    Explanations

    common phrases or prepositions used in geographic or locational contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Cuánto
    -0.70
    ✭✭
    -0.70
    transQ
    -0.66
     Clos
    -0.61
    jusqu
    -0.58
     getNombre
    -0.57
     Saras
    -0.57
    pholes
    -0.57
     Cai
    -0.57
    sizeCache
    -0.56
    POSITIVE LOGITS
    ISTRATION
    0.55
    thâu
    0.55
    tabel
    0.54
    SuppressLint
    0.53
     crois
    0.52
    Beneath
    0.52
     OMITBAD
    0.51
     Harvey
    0.50
    }}],
    0.50
     flore
    0.50
    Act Density 0.025%

    No Known Activations