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

    Neuronpedia

    INDEX
    Explanations

    content related to references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.07
    3:0.08
    4:0.07
    5:0.06
    6:0.08
    7:0.06
    8:0.08
    9:0.09
    10:0.09
    11:0.08
    Negative Logits
     Seb
    -3.76
     Cous
    -3.17
     Masquerade
    -3.11
     Zeit
    -3.01
     Cheong
    -2.92
     Darling
    -2.81
     Spoon
    -2.81
    acist
    -2.78
     Mens
    -2.78
     Ming
    -2.77
    POSITIVE LOGITS
     generator
    3.02
     generators
    2.92
     module
    2.71
     warr
    2.71
     reactor
    2.62
    ugi
    2.59
    module
    2.56
     blocker
    2.55
     player
    2.51
    URI
    2.50
    Act Density 0.000%

    No Known Activations