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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a return or movement back to a previous state or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sure
    -0.36
    One
    -0.34
     Viena
    -0.34
     Pohl
    -0.34
    onych
    -0.32
     sure
    -0.32
    urcht
    -0.31
    టు
    -0.31
     dumne
    -0.31
     One
    -0.31
    POSITIVE LOGITS
     semula
    0.73
     kembali
    0.71
    PageRoute
    0.68
    posedge
    0.67
    again
    0.66
    原始内容存档于
    0.65
     wró
    0.65
     again
    0.64
    ReusableCell
    0.63
     Returning
    0.62
    Act Density 0.259%

    No Known Activations