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

    Neuronpedia

    INDEX
    Explanations

    expressions of collective sentiment and personal connection

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

    Positive sentiment/emotion words

    np_acts-logits-general · gemini-2.0-flash

    express positive feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.60
     transfieras
    -0.57
    featureID
    -0.55
    ();)
    -0.55
     дописавши
    -0.54
    uxxxx
    -0.54
    WriteTagHelper
    -0.53
     newOwner
    -0.50
     leaſt
    -0.50
     newBuilder
    -0.50
    POSITIVE LOGITS
     proud
    1.09
     glad
    1.07
     pleased
    1.01
     thankful
    0.93
     happy
    0.92
     delighted
    0.92
     extremely
    0.90
     grateful
    0.90
     honored
    0.89
     very
    0.85
    Act Density 0.120%

    No Known Activations