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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "been" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ives
    -0.71
    odder
    -0.69
    ively
    -0.68
    robe
    -0.65
    antry
    -0.64
    Sav
    -0.63
    arming
    -0.62
     Uriel
    -0.62
    lies
    -0.61
    vich
    -0.61
    POSITIVE LOGITS
     bitten
    0.92
     proven
    0.85
     able
    0.81
     eaten
    0.81
     replaced
    0.80
     subjected
    0.80
    ĸļ
    0.79
    ī
    0.79
     taken
    0.78
     forgotten
    0.77
    Act Density 0.112%

    No Known Activations