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

    Neuronpedia

    INDEX
    Explanations

    phrases describing benefits and enjoyable experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.74
    argli
    -0.61
    criminator
    -0.59
    Décès
    -0.59
     nhiêu
    -0.58
    deh
    -0.58
    pence
    -0.58
    inaldi
    -0.57
     iload
    -0.57
    alva
    -0.57
    POSITIVE LOGITS
    HasAnnotation
    0.57
    Kjelder
    0.54
    Gambas
    0.52
     genieten
    0.52
    unggulan
    0.47
    enjoy
    0.47
     enjoying
    0.47
     enjoys
    0.45
    ValueStyle
    0.45
     vua
    0.44
    Act Density 0.165%

    No Known Activations