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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confirmation and verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    مقد
    -0.57
    koning
    -0.56
    kloped
    -0.56
    cepan
    -0.52
    BeginContext
    -0.52
    ukunft
    -0.51
    phyllum
    -0.51
     beginnetje
    -0.51
    mistry
    -0.51
    cett
    -0.50
    POSITIVE LOGITS
     confirming
    1.33
     confirms
    1.31
     confirm
    1.28
     confirmation
    1.26
     confirmed
    1.22
     reinforce
    1.17
     confirmations
    1.16
     Confirmation
    1.15
     reaffirm
    1.14
     Confirmed
    1.13
    Act Density 0.585%

    No Known Activations