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

    Neuronpedia

    INDEX
    Explanations

    references to political positions and appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.09
    4:0.10
    5:0.05
    6:0.06
    7:0.13
    8:0.04
    9:0.05
    10:0.24
    11:0.08
    Negative Logits
     explan
    -1.91
    ibaba
    -1.79
    acter
    -1.78
    FTWARE
    -1.69
    pecially
    -1.60
     invitations
    -1.58
    icrobial
    -1.58
    oother
    -1.57
     organis
    -1.56
     Packs
    -1.55
    POSITIVE LOGITS
     Scalia
    1.65
     pseudonym
    1.61
     Scand
    1.59
    wright
    1.57
    eni
    1.54
     Randolph
    1.54
     Reconstruction
    1.52
     vacated
    1.48
     aging
    1.48
     Suff
    1.47
    Act Density 0.000%

    No Known Activations