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

    Neuronpedia

    INDEX
    Explanations

    expressions of love or affinity towards various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.76
    CloseOperation
    -0.74
     aveug
    -0.72
    وأضاف
    -0.71
    gnügen
    -0.69
    ValueGenerated
    -0.69
     hâte
    -0.69
     avulla
    -0.67
    ImageContext
    -0.66
    setVerticalGroup
    -0.65
    POSITIVE LOGITS
     animals
    0.76
     people
    0.61
     nature
    0.59
     outdoors
    0.56
     women
    0.56
     music
    0.54
     cars
    0.52
     photography
    0.52
     water
    0.50
     outdoor
    0.48
    Act Density 0.275%

    No Known Activations