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

    Neuronpedia

    INDEX
    Explanations

    parameters and measurements related to adjustments in experimental setups and dosages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after "adjust" or "adjusted"

    np_acts-logits-general · gemini-2.0-flash

    setting and adjusting values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hield
    -0.54
     nối
    -0.54
    団
    -0.54
    strans
    -0.50
    attached
    -0.47
    円
    -0.47
    gern
    -0.46
     attach
    -0.46
     trans
    -0.46
     attaches
    -0.44
    POSITIVE LOGITS
     adjust
    0.92
     adjustments
    0.91
     adjustment
    0.91
     Adjusting
    0.91
     ajuste
    0.90
     adjusting
    0.90
     Adjust
    0.90
    調整
    0.85
     Ajust
    0.85
     ajust
    0.85
    Act Density 0.480%

    No Known Activations