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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.13
    2:0.05
    3:0.05
    4:0.03
    5:0.05
    6:0.06
    7:0.04
    8:0.04
    9:0.06
    10:0.21
    11:0.15
    Negative Logits
     forfeit
    -2.04
     hosp
    -2.03
     souven
    -1.92
     stopp
    -1.91
     café
    -1.89
     brig
    -1.86
     vacated
    -1.85
     marches
    -1.83
     postponed
    -1.81
     plung
    -1.81
    POSITIVE LOGITS
    NET
    3.63
    NT
    2.55
    COM
    2.50
    Mesh
    2.43
    ANT
    2.42
    TC
    2.40
    framework
    2.39
    lite
    2.39
    Python
    2.34
    CLASS
    2.33
    Act Density 0.000%

    No Known Activations