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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Sam" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oxone
    -0.40
    tedì
    -0.35
     üre
    -0.33
    Dap
    -0.32
    Tikang
    -0.32
    miede
    -0.31
    SAE
    -0.31
    DebuggerNonUser
    -0.31
     indisponible
    -0.31
     Mexique
    -0.30
    POSITIVE LOGITS
     sam
    1.27
     Sam
    1.18
    Sam
    1.16
    SAM
    1.05
    sam
    1.05
     SAM
    1.04
     sampler
    1.00
     Samuel
    0.99
    Samuel
    0.94
     Sample
    0.92
    Act Density 1.835%

    No Known Activations