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

    Neuronpedia

    INDEX
    Explanations

    mentions of grid-related concepts or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uses
    -1.89
     Copyright
    -1.79
     suppose
    -1.78
     supposed
    -1.69
     somebody
    -1.65
     indeed
    -1.62
     shortest
    -1.60
     pronounced
    -1.60
     plaintiff
    -1.58
     chosen
    -1.58
    POSITIVE LOGITS
    aggio
    2.01
    bank
    1.99
    emos
    1.94
    antry
    1.88
    -âĤ¬
    1.87
    âĢIJ
    1.85
    ball
    1.83
    notes
    1.83
    ĻĤ
    1.82
    IFIC
    1.81
    Act Density 0.186%

    No Known Activations