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

    Neuronpedia

    INDEX
    Explanations

    the concept of confirmation or verification within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -0.78
     myſelf
    -0.70
     Jefus
    -0.68
     Efq
    -0.68
    ſelf
    -0.67
     themſelves
    -0.66
     faſt
    -0.64
     foon
    -0.61
     tanga
    -0.61
    ſelves
    -0.60
    POSITIVE LOGITS
    confirm
    1.51
     confirm
    1.44
     Confirm
    1.34
    Confirm
    1.30
     confirmed
    1.26
     confirms
    1.24
    confirmed
    1.21
     Confirmed
    1.18
     confirmé
    1.16
     confirmer
    1.16
    Act Density 0.084%

    No Known Activations