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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "scene" and terms related to visual or environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gradually
    -0.41
     Climb
    -0.40
     commerciales
    -0.40
    inSlope
    -0.39
     gradualmente
    -0.38
    ilever
    -0.38
     Gradually
    -0.36
     cour
    -0.35
    }{*}{}
    -0.35
     ayudará
    -0.35
    POSITIVE LOGITS
     scene
    0.84
    scene
    0.82
     surla
    0.82
     incoming
    0.75
    Incoming
    0.72
     Incoming
    0.71
     autorytatywna
    0.71
     Scene
    0.71
     SCENE
    0.69
    Landscape
    0.68
    Act Density 0.148%

    No Known Activations