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

    Neuronpedia

    INDEX
    Explanations

    instances of doors and related actions of knocking or opening

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Aholisi
    -0.56
     BoxFit
    -0.53
    angliski
    -0.51
    帖最后由
    -0.49
     tartalomajánló
    -0.46
    脚注の使い方
    -0.46
    basicConfig
    -0.45
    libft
    -0.43
    ########.
    -0.42
     EClass
    -0.42
    POSITIVE LOGITS
     door
    3.34
     doors
    3.08
     Door
    2.73
    door
    2.73
    Door
    2.69
     DOOR
    2.64
     Doors
    2.53
    doors
    2.53
    Doors
    2.38
     puerta
    2.27
    Act Density 0.332%

    No Known Activations