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

    Neuronpedia

    INDEX
    Explanations

    repeated references to "scene" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :+:
    -0.56
    numerusform
    -0.49
     porcel
    -0.46
    chemic
    -0.46
    estim
    -0.45
    estic
    -0.44
    卒
    -0.44
    orithms
    -0.44
    ########.
    -0.43
    adeloupe
    -0.43
    POSITIVE LOGITS
     escenas
    0.62
     scènes
    0.58
     Scenes
    0.57
     scene
    0.54
     Scene
    0.53
     boil
    0.52
     actualidad
    0.51
     sekali
    0.50
     escena
    0.49
     scène
    0.49
    Act Density 0.346%

    No Known Activations