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

    Neuronpedia

    INDEX
    Explanations

    the word "Beck" with varied activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Beck."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntil
    -0.88
    ocre
    -0.80
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.71
     unnecess
    -0.70
    rely
    -0.68
     ACTION
    -0.67
    ricular
    -0.65
    âĶĢâĶĢâĶĢâĶĢ
    -0.62
    ctic
    -0.61
    AMES
    -0.61
    POSITIVE LOGITS
    ett
    1.08
    etts
    1.08
    erman
    1.07
     Beck
    1.07
    mann
    1.01
    stra
    0.99
    oning
    0.98
    ford
    0.98
    enstein
    0.98
    strap
    0.97
    Act Density 0.029%

    No Known Activations