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

    Neuronpedia

    INDEX
    Explanations

    code syntax and programming-related elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.79
     reaſon
    -0.78
     ſche
    -0.77
     purpoſe
    -0.76
     ſtate
    -0.74
     Doy
    -0.71
     houſe
    -0.71
     pleaſure
    -0.71
     ſte
    -0.71
     McIl
    -0.70
    POSITIVE LOGITS
    
    1.08
    loroethene
    0.69
     Assignment
    0.68
    Bindings
    0.64
     assignment
    0.63
     Assignments
    0.63
    assignment
    0.63
    espan
    0.63
    ETHING
    0.61
    aphne
    0.59
    Act Density 0.000%

    No Known Activations