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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "confirm" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ineno
    -0.57
    uxxxx
    -0.55
    aarrggbb
    -0.53
     v
    -0.53
     iprot
    -0.53
    JsonInclude
    -0.52
     beginnetje
    -0.52
     par
    -0.52
    rées
    -0.52
    astră
    -0.51
    POSITIVE LOGITS
     confirmation
    2.72
     confirm
    2.67
     confirming
    2.58
     confirmed
    2.56
     confirms
    2.47
     verify
    2.45
     confirmations
    2.44
     Confirm
    2.43
     Confirmation
    2.38
     verified
    2.37
    Act Density 0.102%

    No Known Activations