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

    Neuronpedia

    INDEX
    Explanations

    references to special events and terms related to specific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Portale
    -0.82
    IContainer
    -0.81
     autorytatywna
    -0.79
     defaultstate
    -0.75
     nahilalakip
    -0.73
    InjectAttribute
    -0.72
     pinulongan
    -0.70
    PerformLayout
    -0.69
     Roskov
    -0.68
     dialec
    -0.65
    POSITIVE LOGITS
     quick
    0.63
     extra
    0.61
     special
    0.57
     short
    0.57
     Quick
    0.52
    quick
    0.52
     post
    0.51
    Quick
    0.51
    short
    0.49
     pre
    0.48
    Act Density 0.249%

    No Known Activations