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

    Neuronpedia

    INDEX
    Explanations

    instances of deafeningly loud content

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.92
    Bains
    -0.86
    ינוך
    -0.81
     GeoNames
    -0.78
    很想
    -0.78
     ★
    -0.77
     Wikispecies
    -0.76
    ^*)
    -0.73
    servez
    -0.72
     rootView
    -0.72
    POSITIVE LOGITS
    rd
    1.26
            
    1.16
    3
    0.95
     SDP
    0.89
     tercio
    0.87
                            
    0.82
    Dar
    0.81
    Datuak
    0.79
     Comer
    0.78
    ۳
    0.77
    Act Density 0.193%

    No Known Activations