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

    Neuronpedia

    INDEX
    Explanations

    terms indicating significance or importance across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ']?>
    -0.81
    ']}
    -0.75
    tik
    -0.66
    )}=
    -0.64
    :],
    -0.61
     }}$
    -0.61
    "/>
    -0.61
    ]}
    -0.60
    }/>
    -0.59
    ()}
    -0.57
    POSITIVE LOGITS
    major
    1.61
     MAJOR
    1.56
    MAJOR
    1.56
    Major
    1.51
     major
    1.48
     Major
    1.47
     majors
    1.39
     Majors
    1.38
    maj
    1.23
    Minor
    1.16
    Act Density 0.043%

    No Known Activations