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

    Neuronpedia

    INDEX
    Explanations

    phrases related to copyright and permissions for images

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.57
     l
    -0.56
     j
    -0.51
     p
    -0.50
    <sup>
    -0.49
     Gar
    -0.49
     f
    -0.48
     everything
    -0.48
     big
    -0.48
    <em>
    -0.47
    POSITIVE LOGITS
     saites
    1.06
     myſelf
    1.00
     Efq
    0.97
     useAppContext
    0.96
     pleaſure
    0.95
    MLLoader
    0.94
     Jefus
    0.94
    uxxxx
    0.93
     MainAxisSize
    0.92
    InjectAttribute
    0.90
    Act Density 0.568%

    No Known Activations