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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and well-wishing within messages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    stdc
    -0.69
    Ligações
    -0.60
    arithmic
    -0.59
    ogados
    -0.57
    halter
    -0.57
    PYX
    -0.57
     onResponse
    -0.56
    NameInMap
    -0.56
    arikat
    -0.56
     باخ
    -0.56
    POSITIVE LOGITS
    Tikang
    0.61
    ValueStyle
    0.56
    Diwedd
    0.53
    فسير
    0.48
    Dearest
    0.47
     kanyang
    0.47
    bootstrapcdn
    0.46
    </blockquote>
    0.44
    opensource
    0.43
     specchio
    0.43
    Act Density 0.016%

    No Known Activations