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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or going back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.92
    krit
    -0.82
    afety
    -0.80
    anguard
    -0.78
    obal
    -0.77
    ku
    -0.76
    eller
    -0.73
    someone
    -0.73
    7601
    -0.73
    ISSION
    -0.72
    POSITIVE LOGITS
     editions
    1.05
     successive
    1.04
     seasons
    0.99
     consecutive
    0.96
     victories
    0.95
     halves
    0.93
     sessions
    0.90
     episodes
    0.90
     nights
    0.85
     versions
    0.84
    Act Density 0.010%

    No Known Activations