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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal favorites and seasonal appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acin
    -0.18
    546
    -0.14
    -corner
    -0.14
    utral
    -0.14
    abra
    -0.14
    AXB
    -0.14
    /help
    -0.13
    ãģĵãģ¨ãģ«
    -0.13
     yours
    -0.13
    amac
    -0.13
    POSITIVE LOGITS
     my
    0.75
    my
    0.62
    æĪijçļĦ
    0.54
    =my
    0.52
    (my
    0.51
    	my
    0.49
     mijn
    0.44
    -my
    0.41
    .my
    0.41
     favorites
    0.41
    Act Density 0.195%

    No Known Activations