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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a duration of time or periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ownik
    -0.18
    оваÑĢи
    -0.16
    éŀ
    -0.15
    rary
    -0.15
    onium
    -0.14
    µľ
    -0.14
    ekil
    -0.14
     Setter
    -0.14
    inesis
    -0.14
    ugh
    -0.14
    POSITIVE LOGITS
     initial
    0.21
     struggle
    0.18
    YPE
    0.18
     failed
    0.18
     awhile
    0.17
     initially
    0.17
    uria
    0.17
     deliber
    0.17
     false
    0.16
     successful
    0.16
    Act Density 0.109%

    No Known Activations