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

    Neuronpedia

    INDEX
    Explanations

    references to crafting and design activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſch
    -0.71
     oftentimes
    -0.63
     réfrig
    -0.61
    ſand
    -0.59
    haviors
    -0.59
    ſchen
    -0.58
     mauva
    -0.58
     verſ
    -0.57
    —”
    -0.57
     esimerkiksi
    -0.57
    POSITIVE LOGITS
     bloke
    0.89
     !!!!
    0.88
     dodgy
    0.85
     !!!!!
    0.85
     !!!!!!
    0.83
    Whilst
    0.81
     daft
    0.81
     !!
    0.80
     IMHO
    0.80
    :-
    0.80
    Act Density 0.624%

    No Known Activations