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

    Neuronpedia

    INDEX
    Explanations

    references to financial responsibility or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.08
    3:0.05
    4:0.14
    5:0.02
    6:0.02
    7:0.45
    8:0.02
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
    Appearance
    -2.11
    ourage
    -1.86
    uron
    -1.71
    enment
    -1.69
    ularity
    -1.68
    colour
    -1.62
    enery
    -1.60
    emale
    -1.57
    emin
    -1.54
    nob
    -1.53
    POSITIVE LOGITS
     trespass
    2.01
     extortion
    1.94
     debts
    1.93
     costly
    1.89
     loans
    1.89
     ransom
    1.84
     tresp
    1.81
     smugglers
    1.81
     theft
    1.77
     contingency
    1.73
    Act Density 0.001%

    No Known Activations