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

    Neuronpedia

    INDEX
    Explanations

    indicators of ongoing investigations or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.05
    3:0.13
    4:0.08
    5:0.04
    6:0.05
    7:0.03
    8:0.10
    9:0.07
    10:0.10
    11:0.22
    Negative Logits
     Sta
    -1.70
    etz
    -1.67
     Faul
    -1.60
    YA
    -1.60
    DM
    -1.60
     oun
    -1.59
    gew
    -1.55
    oaded
    -1.54
    DN
    -1.54
    pled
    -1.51
    POSITIVE LOGITS
    levard
    1.96
     hippocampus
    1.92
     thriller
    1.82
     trillion
    1.81
     nanop
    1.74
    Reuters
    1.74
    thereum
    1.73
     ripple
    1.71
     glitch
    1.68
    hran
    1.67
    Act Density 0.003%

    No Known Activations