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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference and the act of noticing or perceiving details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geſ
    -0.63
     desmotivaciones
    -0.59
    pecabe
    -0.58
     Gedicht
    -0.58
     miniaturka
    -0.57
     reflexiones
    -0.56
     plufieurs
    -0.54
     Bewußt
    -0.54
     animación
    -0.54
    ágenes
    -0.54
    POSITIVE LOGITS
     Prefer
    0.69
     notice
    0.68
    Notice
    0.66
    OUT
    0.66
     prefer
    0.64
    Prefer
    0.62
    Modified
    0.61
     Appreciate
    0.61
    LES
    0.61
    Appreciate
    0.60
    Act Density 0.222%

    No Known Activations