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

    Neuronpedia

    INDEX
    Explanations

    references to small scale or limited quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to "small."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĥ
    -0.75
    lain
    -0.71
    reon
    -0.69
    oother
    -0.68
    raints
    -0.68
    çīĪ
    -0.66
    Reviewed
    -0.66
    erion
    -0.65
    efe
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
    POSITIVE LOGITS
    pox
    1.04
     consolation
    0.94
     sized
    0.92
     intestine
    0.90
     fry
    0.89
    tiny
    0.87
     insignificant
    0.83
     small
    0.79
    heartedly
    0.78
     fraction
    0.78
    Act Density 0.028%

    No Known Activations