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

    Neuronpedia

    INDEX
    Explanations

    repetitive uses of the word "okay" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poichè
    -0.55
     Aborig
    -0.48
    inescence
    -0.48
    XLS
    -0.47
     bds
    -0.47
     Tr
    -0.47
     sya
    -0.47
    Vlad
    -0.47
     iscri
    -0.47
    ṳ
    -0.46
    POSITIVE LOGITS
    okay
    1.55
     okay
    1.49
    Okay
    1.48
     OKAY
    1.41
     Okay
    1.37
    OKAY
    1.24
    alright
    0.64
     Équipe
    0.60
     myſelf
    0.59
    ًا
    0.58
    Act Density 0.098%

    No Known Activations