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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses and expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.61
     Majefty
    -0.60
     Bany
    -0.57
    çons
    -0.56
     whiche
    -0.56
    Skocz
    -0.56
    felves
    -0.56
    hdashline
    -0.55
    OLPH
    -0.55
    anik
    -0.55
    POSITIVE LOGITS
    GEBURTSDATUM
    0.79
     indeed
    0.73
    Yep
    0.72
     yep
    0.72
    ScopeManager
    0.71
    yup
    0.70
     Yep
    0.69
    yep
    0.68
     متعلقه
    0.68
    yes
    0.63
    Act Density 0.086%

    No Known Activations