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

    Neuronpedia

    INDEX
    Explanations

    words associated with signing documents or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    piecze
    -0.65
     Référence
    -0.64
     malheureusement
    -0.63
    veille
    -0.61
     concr
    -0.61
    endroit
    -0.60
     oublier
    -0.59
     frumo
    -0.58
     EconPapers
    -0.57
     encontraban
    -0.57
    POSITIVE LOGITS
     signed
    1.22
    signed
    1.07
     attack
    1.03
     Signed
    1.02
     signing
    1.01
    Signed
    0.96
     Sig
    0.96
     Sign
    0.94
     SIGN
    0.94
    Sig
    0.92
    Act Density 0.083%

    No Known Activations