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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a recurring or frequent action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whenever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asse
    -0.79
    atories
    -0.75
    mber
    -0.71
    heimer
    -0.70
    yp
    -0.70
    illard
    -0.67
    asc
    -0.67
    ocker
    -0.66
    ymph
    -0.66
    oult
    -0.65
    POSITIVE LOGITS
    soever
    1.40
     imaginable
    0.93
     practicable
    0.92
     else
    0.92
    theless
    0.83
     possible
    0.82
     thereafter
    0.81
    wcsstore
    0.77
    ãĤ¼ãĤ¦ãĤ¹
    0.76
     feasible
    0.75
    Act Density 0.013%

    No Known Activations