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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidance or direction in life

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nick
    -0.64
    pots
    -0.63
    iston
    -0.60
     recept
    -0.59
    ufficient
    -0.59
    âĶĢâĶĢâĶĢâĶĢ
    -0.58
     tipped
    -0.58
    acceptable
    -0.58
     conditional
    -0.58
     feared
    -0.57
    POSITIVE LOGITS
     journey
    0.92
     journeys
    0.85
     travels
    0.85
     travelled
    0.83
     toward
    0.83
     Steps
    0.82
    Route
    0.82
     traveled
    0.82
     trek
    0.81
     onward
    0.81
    Act Density 0.467%

    No Known Activations