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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of occurrence, predictions, or conditions over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthand
    -0.13
    rezent
    -0.13
    izr
    -0.13
    еÑĤÑģÑı
    -0.12
    tual
    -0.12
    еÑĢÑĤа
    -0.12
    βάλ
    -0.12
    оваÑĤелÑĮ
    -0.12
     erken
    -0.12
    logic
    -0.12
    POSITIVE LOGITS
     last
    1.09
    last
    0.91
     Last
    0.88
    Last
    0.87
    -last
    0.84
    _last
    0.84
    .last
    0.82
     LAST
    0.82
    	last
    0.76
    (last
    0.72
    Act Density 0.308%

    No Known Activations