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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or going back to a previous state or place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kloped
    -0.79
    migrationBuilder
    -0.69
    chaun
    -0.69
    ősz
    -0.68
    StrictEqual
    -0.66
    contentLoaded
    -0.64
    rature
    -0.64
    MLLoader
    -0.64
     kiệm
    -0.64
    StoreMessageInfo
    -0.64
    POSITIVE LOGITS
     rejoined
    0.77
    回到了
    0.75
     reverting
    0.75
    回到
    0.74
     back
    0.73
     revert
    0.71
    返
    0.71
    back
    0.70
    に戻
    0.70
     revisit
    0.69
    Act Density 0.190%

    No Known Activations