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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or going back to previous points or states

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

    Phrase "back to" or a return

    np_acts-logits-general · gemini-2.0-flash

    return or go back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.82
    ècie
    -0.73
     Himo
    -0.69
    WillAppear
    -0.66
    urably
    -0.65
    mazan
    -0.65
     adicionais
    -0.64
    URLException
    -0.64
    ftagPool
    -0.64
    oredCriteria
    -0.64
    POSITIVE LOGITS
    回到了
    0.67
     again
    0.66
     back
    0.64
     rejoined
    0.63
     eski
    0.59
     normality
    0.58
     lagi
    0.56
     regaining
    0.56
     restoring
    0.55
     resumed
    0.55
    Act Density 0.148%

    No Known Activations