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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating customer appreciation and trust

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    thank you for choosing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Попис
    -0.45
     digress
    -0.41
    ])):
    -0.36
    })->
    -0.36
     Савезне
    -0.35
    aspectj
    -0.32
    '))
    -0.31
    %"),
    -0.30
     volna
    -0.30
    /*!
    -0.30
    POSITIVE LOGITS
     choice
    1.68
     choose
    1.64
     choosing
    1.63
     chooses
    1.54
    choice
    1.50
     chose
    1.50
    choosing
    1.49
    choose
    1.48
     Choose
    1.47
    Choose
    1.46
    Act Density 0.033%

    No Known Activations