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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal proceedings and official documents

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to numerical data and statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Quantity
    -0.74
    stress
    -0.67
     stabilization
    -0.64
     stimulation
    -0.63
    itive
    -0.63
     competitor
    -0.61
    ishment
    -0.60
     setback
    -0.60
     stimulus
    -0.60
    ainment
    -0.60
    POSITIVE LOGITS
     whom
    1.05
    who
    0.92
     alike
    0.85
    whose
    0.77
    vae
    0.76
    doms
    0.76
    edIn
    0.76
     respectively
    0.76
    ©¶æ¥µ
    0.74
    conserv
    0.73
    Act Density 1.329%

    No Known Activations